Staff Software Engineer (Environments Infrastructure)

Join Anthropic, a leading AI safety and research company, as a Staff Software Engineer in the Environments Infrastructure team. You will design and build frameworks and APIs that enhance Claude's capabilities through reinforcement learning. Your work will involve embedding with research teams, maintaining production RL runs, and driving the adoption of new frameworks across the organization. You should have deep expertise in Python, a strong sense of API and framework design, and a good intuition for complex systems.

• Conception et mise en œuvre d'API, de frameworks et d'abstractions largement utilisés par d'autres ingénieurs et chercheurs.
• Responsabilité des couches de plateforme qui se trouvent sous chaque environnement, y compris l'exécution de l'agent.
• Conception d'une abstraction de base pour l'environnement RL qui peut être sous-classée pour prendre en charge la grande majorité des environnements.
• Experience working productively in large, evolving, or research-style codebases that you didn't originally write
• Deep expertise in Python, including static typing, safe async and concurrency patterns, and writing performant code
• Strong taste in API and framework design, the ability to explain why an interface is right or wrong rather than just recognizing it, and a track record of other engineers or teams adopting and building on frameworks you have built
• Experience designing serialization schemes, plugin systems, or extensible class hierarchies used across an organization
• Experience embedding with or consulting for other teams and handing off systems for others to own, or defining code standards adopted across teams, or prior experience as a technical lead
• Strong written and verbal communication with collaborators of varied engineering backgrounds, and comfort with ambiguity: able to scope your own work from a loosely defined problem and drive it to a maintainable outcome
• Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
• A habit of verification: you measure before you conclude, and you build the checks that let a system show it's correct
• Experience using AI coding tools on code where correctness matters, with good judgment about what to delegate and how to make the results verifiable
• Experience building agent frameworks, orchestration engines, or multi-agent systems, including checkpoint and restore, replay, and coordination of long-running stateful processes
• Experience building infrastructure, tooling, or frameworks for machine learning research or RL workflows, and familiarity with agentic systems or LLM training pipelines
• Experience designing or operating stateful concurrent or distributed systems, and reasoning carefully about failure, retires, idempotency, and consistency
• Experience building client libraries or SDKs on top of sandboxed, containerized, or remote execution platforms
• Experience with large-scale data processing, dataset lifecycle management, or data lineage systems