Full-Stack Software Engineer, Reinforcement Learning
Anthropic · San Francisco, CA | New York City · Onsite
Anthropic
Anthropic is an AI safety and research company founded in 2021 by former OpenAI executives, including siblings Dario and Daniela Amodei, who left to pursue a more safety-focused approach to building powerful AI systems. Its flagship product, the Claude family of large language models, competes directly with OpenAI's GPT series and Google's Gemini, and has become widely used in enterprise and developer settings, particularly for coding and reasoning tasks. The company positions itself distinctly within the AI industry by emphasizing interpretability and alignment research alongside commercial deployment, framing itself as a lab racing to build capable frontier models while trying to ensure they remain steerable and beneficial as capabilities scale.
Gig description
About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. About the Role As a Full-Stack Software Engineer in RL, you'll build the platforms, tools, and interfaces that power environment creation, data collection, and training observability. The quality of Claude's next generation depends on the quality of the data we train it on — and the systems you build are what make that data possible. You'll own product surfaces end-to-end — from backend services and APIs to the web UIs that researchers, external vendors, and thousands of data labelers use every day. You don't need a background in ML research. What matters is that you can take an ambiguous, high-stakes problem and ship a polished, reliable product against it, fast. This team moves very quickly. Claude writes a lot of the code we commit, which means the bottleneck isn't typing — it's judgment, taste, and the ability to react to what researchers need next. You'll iterate on data collection strategies to distill the knowledge of thousands of human experts around the world into our models, and you'll do it in a loop that closes in hours and days, not quarters or months. Anthropic's Reinforcement Learning organization leads the research and development that trains Claude to be capable, reliable, and safe. We've contributed to every Claude model, with significant impact on the autonomy and coding capabilities of our most advanced models. Our work spans teaching models to use computers effectively, advancing code generation through RL, pioneering fundamental RL research for large language models, and building the scalable training methodologies behind our frontier production models. The RL org is organized around four goals: solving the science of long-horizon tasks and continual learning, scaling RL data and environments to be comprehensive and diverse, automating software engineering end-to-end, and training the frontier production model. Our engineering teams build the environments, evaluation systems, data pipelines, and tooling that make all of this possible — from realistic agentic training environments and scalable code data generation to human data collection platforms and production training operations. What You'll Do Build and extend web platforms for RL environment creation, management, and quality review — including environment configuration, versioning, and validation workflows Develop vendor-facing interfaces and tooling that let external partners create, submit, and iterate on training environments with minimal friction Design and implement platforms for human data collection at scale, including labeling workflows, quality assurance systems, and feedback mechanisms that surface reward signal integrity issues early Build evaluation dashboards and observability UIs that give researchers real-time insight into environment quality, training run health, and reward hacking Create backend services and APIs that connect environment authoring tools, data collection systems, and RL training infrastructure Build and expand scalable code data generation pipelines, producing diverse programming tasks with robust reward signals across languages and difficulty levels Develop onboarding automation and documentation tooling so new vendors and internal users ramp up in hours, not weeks Partner closely with RL researchers, data operations, and vendor management to translate ambiguous requirements into well-scoped, well-designed products You May Be a Good Fit If You Have strong software engineering fundamentals and real full-stack range — you're comfortable owning a surface from database schema to frontend Are proficient in Python and a modern web stack (React, TypeScript, or similar) Have a track record of shipping systems that solved a hard problem , not just shipped on time — e. g. you built the thing that made your team 10x faster, or the internal tool nobody thought was possible Operate with high agency: you identify what needs to be done and drive it forward without waiting for a ticket Have found yourself wondering "why isn't this moving faster? " in previous roles — and then have done something about it Care about UX and can build interfaces that are intuitive for both technical researchers and non-technical labelers Communicate clearly with researchers, operations teams, and engineers, and can turn vague asks into well-scoped work Thrive in a fast-moving environment where priorities shift, Claude is your pair programmer, and the next problem is often one nobody has solved before Care about Anthropic's mission to build safe, beneficial AI and want your work to contribute directly to it Strong Candidates May Also Have Built data collection, labeling, or annotation platforms — ideally ones that had to scale across many vendors or many task types Background building multi-tenant platforms with role-based access, audit trails, and vendor management workflows Experience with cloud infrastructure (GCP or AWS), Docker, and CI/CD pipelines Familiarity with LLM training, fine-tuning, or evaluation workflows Experience with async Python (Trio, asyncio) or high-throughput API design Background in dashboards, monitoring, or observability tooling Experience working directly with external vendors or partners on technical integrations A background that isn't a straight line — e. g. math or physics into SWE, competitive programming, research into engineering, or a side project that outgrew its scope Representative Projects Building a unified platform for human data collection that integrates labeling workflows, vendor management, and QA for complex agentic tasks Developing vendor onboarding automation that handles Docker registry access, API token management, and environment validation Creating evaluation and observability dashboards that catch reward hacks, measure environment difficulty, and give real-time feedback during production training Building environment quality review workflows that let researchers browse, grade, and provide feedback on training environments Developing automated environment quality pipelines that validate correctness and difficulty calibration before environments hit production training Building internal tools for browsing and analyzing training run results, environment statistics, and data collection progress The annual compensation range for this role is listed below. For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role. Annual Salary: $300,000 — $405,000 USD Logistics Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices. Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this. We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team. Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic. com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic. com/careers directly for confirmed position openings. How we're different We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills. The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences. Come work with us! Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process.
Requirements to meet
Disclaimer
Suggestions only — review each course yourself to judge whether it meets the role's requirements. Completing a course doesn't guarantee proficiency or that you'll qualify; hiring standards vary by employer.
Skills required
Fine-Tuning (required)
GapCourses that may help you meet this requirement:
Generative AI Advanced Fine-Tuning for LLMs
Coursera · intermediate · $49/mo · 9h · ★ 4.4
This course directly covers Fine-Tuning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 9 hours.
Hugging Face NLP Course
Hugging Face Learn · intermediate · Free
This course directly covers Fine-Tuning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level.
Optimize and fine-tune AI agents for production
Microsoft Learn · intermediate · Free · 1.5h
This intermediate course directly covers fine-tuning techniques, addressing the Fine-Tuning skill gap required for the Full-Stack Software Engineer, Reinforcement Learning role.
Machine Learning (required)
GapCourses that may help you meet this requirement:
Introduction to DevOps principles for machine learning
Microsoft Learn · beginner · Free · 33m · ★ 4.7
This course directly covers Machine Learning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 1 hours.
Continuous deployment for machine learning
Microsoft Learn · beginner · Free · 22m · ★ 4.7
This course directly covers Machine Learning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 0 hours.
Intro to Machine Learning
Kaggle Learn · beginner · Free
This course directly covers Machine Learning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level.
Agentic Workflows (required)
GapCourses that may help you meet this requirement:
AI Agents and Agentic AI with Python & Generative AI
Coursera · beginner · $49/mo · 11h · ★ 4.6
This course directly covers Agentic Workflows, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 11 hours.
Understand features of Copilot Studio agents
Microsoft Learn · beginner · Free · 54m
This course covers Agentic Workflows, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 1 hours.
Hugging Face Agents Course
Hugging Face Learn · intermediate · Free
This course covers Agentic Workflows, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level.
Python (required)
GapCourses that may help you meet this requirement:
PySpark & Python: Hands-On Guide to Data Processing
Coursera · beginner · $49/mo · 5h · ★ 4.4
This course directly covers Python, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 5 hours.
Data Analysis with Python
freeCodeCamp · beginner · Free
This course directly covers Python, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level.
Pandas
Kaggle Learn · beginner · Free
This beginner Pandas course helps build foundational Python skills needed for the Full-Stack Software Engineer, Reinforcement Learning role.
TypeScript (required)
GapCourses that may help you meet this requirement:
Modern Web Development with TypeScript Specialization
Coursera · beginner · $49/mo · 60h · ★ 4.7
This course directly covers TypeScript, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 60 hours.
Introduction to Angular
Coursera · beginner · $49/mo · 5h
This course directly covers TypeScript, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 5 hours.
Learn Typescript
Coursera · intermediate · $49/mo · 5h · ★ 4.5
This course directly covers TypeScript, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 5 hours.
AWS (required)
GapCourses that may help you meet this requirement:
AWS Fundamentals Specialization
Coursera · beginner · $49/mo · 40h · ★ 4.8
This course covers AWS, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 40 hours.
AWS Cloud Technical Essentials
Coursera · beginner · $49/mo · 20h · ★ 4.8
This course covers AWS, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 20 hours.
AWS Cloud Solutions Architect Professional Certificate
Coursera · intermediate · $49/mo · 62h · ★ 4.8
This course covers AWS, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 62 hours.
GCP (required)
GapCourses that may help you meet this requirement:
Google Cloud Fundamentals: Core Infrastructure
Coursera · beginner · Price on site · 6h · ★ 4.7
This course covers GCP, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 6 hours.
Data Engineering, Big Data, and Machine Learning on GCP Specialization
Coursera · intermediate · $49/mo · 31h · ★ 4.6
This course covers GCP, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 31 hours.
Machine Learning Operations (MLOps) on Google Cloud Specialization
Coursera · intermediate · $49/mo · 16h · ★ 4.0
This course covers GCP, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 16 hours.
Docker (required)
GapCourses that may help you meet this requirement:
Build a containerized web application with Docker
Microsoft Learn · beginner · Free · 57m · ★ 4.6
This course directly covers Docker, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 1 hours.
Docker for Beginners with Hands-on labs
Coursera · beginner · $49 · 10h · ★ 4.6
This course directly covers Docker, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 10 hours.
Leverage GitHub Actions to publish to GitHub Packages
Microsoft Learn · intermediate · Free · 41m · ★ 4.8
This intermediate course covers Docker, directly addressing the Docker skill gap identified for the Full-Stack Software Engineer, Reinforcement Learning role.
Statistics (required)
GapCourses that may help you meet this requirement:
Statistics Foundations
Coursera · beginner · $49/mo · 23h · ★ 4.8
This course directly covers Statistics, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 23 hours.
Introduction to Statistics
Coursera · beginner · $79 · 13h · ★ 4.6
This course directly covers Statistics, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 13 hours.
How to Process, Analyze and Visualize Data
MIT Learn · beginner · Free
This beginner course is recommended to help build foundational Statistics skills needed for the Full-Stack Software Engineer, Reinforcement Learning role, though specific topic coverage details are not provided.
Large Language Models (required)
GapCourses that may help you meet this requirement:
Leverage AI tools and resources for your business
Microsoft Learn · beginner · Free · 42m · ★ 4.8
This course covers Large Language Models, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 1 hours.
Explore data roles and services
Microsoft Learn · beginner · Free · 22m · ★ 4.8
This course covers Large Language Models, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 0 hours.
Use AI for everyday tasks
Microsoft Learn · beginner · Free · 43m
This beginner course on using AI for everyday tasks is recommended to help build foundational familiarity with Large Language Models, addressing a key skill gap for the Full-Stack Software Engineer, Reinforcement Learning role.
Reinforcement Learning (required)
GapCourses that may help you meet this requirement:
Unsupervised Learning, Recommenders, Reinforcement Learning
Coursera · beginner · $49/mo · 30h · ★ 4.9
This course directly covers Reinforcement Learning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 30 hours.
Generative AI with Large Language Models
Coursera · intermediate · $49 · 17h · ★ 4.8
This course covers Reinforcement Learning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 17 hours.
Fundamentals of Reinforcement Learning
Coursera · intermediate · $79/mo · 15h · ★ 4.8
This course directly covers Reinforcement Learning, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 15 hours.
Distributed Training (required)
GapCourses that may help you meet this requirement:
Custom and Distributed Training with TensorFlow
Coursera · intermediate · $49/mo · 24h · ★ 4.8
This course directly covers Distributed Training, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 24 hours.
Transformer Architectures and Multimodal Models
Coursera · intermediate · $49/mo · 11h
This course directly covers Distributed Training, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 11 hours.
React (required)
GapCourses that may help you meet this requirement:
Meta Front-End Developer Professional Certificate
Coursera · beginner · $49/mo · 229h · ★ 4.7
This course covers React, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 229 hours.
React Basics
Coursera · beginner · $49/mo · 28h · ★ 4.7
This course directly covers React, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 28 hours.
Advanced React
Coursera · intermediate · $49/mo · 26h · ★ 4.6
This course directly covers React, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an intermediate level and can be completed in approximately 26 hours.
CI/CD (required)
GapCourses that may help you meet this requirement:
Introduction to Git
Microsoft Learn · beginner · Free · 1.5h · ★ 4.8
This course lacks any matched keywords or content evidence related to CI/CD, so it cannot be confidently recommended to address that specific skill gap for the Full-Stack Software Engineer, Reinforcement Learning role.
Introduction to DevOps principles for machine learning
Microsoft Learn · beginner · Free · 33m · ★ 4.7
This course covers CI/CD, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 1 hours.
Introduction to GitHub Copilot Business
Microsoft Learn · beginner · Free · 23m · ★ 4.7
This course covers CI/CD, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 0 hours.
ETL (required)
GapCourses that may help you meet this requirement:
Explore data roles and services
Microsoft Learn · beginner · Free · 22m · ★ 4.8
This course covers ETL, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 0 hours.
Explore fundamentals of large-scale analytics
Microsoft Learn · beginner · Free · 51m · ★ 4.8
This course covers ETL, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 1 hours.
The Path to Insights: Data Models and Pipelines
Coursera · advanced · $49/mo · 17h · ★ 4.7
This course covers ETL, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at an advanced level and can be completed in approximately 17 hours.
Quality Management (required)
GapCourses that may help you meet this requirement:
Six Sigma Tools for Improve and Control
Coursera · beginner · $49/mo · 7h · ★ 4.7
This course covers Quality Management, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 7 hours.
Introduction to Operations Management
Coursera · beginner · $79/mo · 16h · ★ 4.5
This course directly covers Quality Management, which appears as a requirement in the Full-Stack Software Engineer, Reinforcement Learning posting at a beginner level and can be completed in approximately 16 hours.
Describe inventory management in Dynamics 365 Supply Chain Management
Microsoft Learn · beginner · Free · 1h
This beginner course touches on management and quality concepts, helping address the Quality Management skill gap for the Full-Stack Software Engineer, Reinforcement Learning role.