Full-Stack Software Engineer, Reinforcement Learning

Details

Anthropic’s Reinforcement Learning (RL) organization builds the platforms, tools, and interfaces that power environment creation, large-scale data collection, and training observability for Claude. This role owns product surfaces end-to-end — from backend services and APIs to web UIs used by researchers, external vendors, and thousands of data labelers. You do not need an ML research background; the focus is on shipping polished, reliable full‑stack systems that enable high-quality training data and scalable RL pipelines.

Responsibilities

• Build and extend web platforms for RL environment creation, configuration, versioning, and validation workflows
• Develop vendor-facing interfaces and tooling for external partners to create, submit, and iterate on training environments
• Design and implement platforms for human data collection at scale: labeling workflows, QA systems, and feedback mechanisms to surface reward-signal integrity issues
• Build evaluation dashboards and observability UIs giving researchers real-time insights into environment quality, training run health, and reward hacking
• Create backend services and APIs connecting environment authoring tools, data collection systems, and RL training infrastructure
• Build and expand scalable code data generation pipelines producing diverse programming tasks across languages and difficulty levels
• Develop onboarding automation and documentation tooling for rapid ramp-up of vendors and internal users
• Partner closely with RL researchers, data operations, and vendor management to translate ambiguous requirements into well-scoped, well-designed products

Requirements

• Strong software engineering fundamentals with real full-stack experience (database schema through frontend)
• Proficiency in Python and a modern web stack (React, TypeScript, or similar)
• Experience building reliable backend services and APIs
• Demonstrated track record of shipping systems that solved hard problems and improved team throughput
• Strong product and UX sensibility for both technical researchers and non-technical labelers
• Excellent communication skills and ability to translate vague asks into scoped work
• Ability to operate with high agency in a fast-moving environment

Preferred / Nice-to-Have

• Experience building data collection, labeling, or annotation platforms at scale
• 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

Representative Projects

• Unified platform for human data collection integrating labeling workflows, vendor management, and QA
• Vendor onboarding automation handling Docker registry access, API token management, and environment validation
• Evaluation and observability dashboards that detect reward hacks and measure environment difficulty
• Environment quality review workflows and automated validation pipelines before production training

Compensation

• Annual salary range: $300,000 - $405,000 USD

Logistics

• Minimum education: Bachelor’s degree or equivalent combination of education/training/experience
• Minimum years of experience: correlates with internal job level requirements
• Location-based hybrid policy: staff expected to be in one of our offices at least 25% of the time (some roles may require more)
• Visa sponsorship: Anthropic states they do sponsor visas and retain an immigration lawyer to assist, though sponsorship is not guaranteed for every role/candidate