Staff Software Engineer - RL Frameworks & Tooling

Anthropic Limited; New York (NY); Hybrid; USD 405,000 - 625,000; Full time

Job summary

Anthropic is seeking an experienced engineer to shape reinforcement learning tooling and APIs for agentic coding environments. You will embed with research teams, design frameworks, and maintain production RL runs. Strong Python, API design, and the ability to work in large codebases are essential.

Location-based hybrid policy requires in-office presence at least 25% of the time. You’ll collaborate across engineers and researchers, translating research needs into robust, scalable software that

Qualifications

• Bachelor’s degree in a field relevant to the role.
• Strong Python expertise and ability to design APIs.
• Experience with research-style or large codebases.

Responsibilities

• Design widely-used APIs, frameworks, and abstractions for engineers and researchers.
• Embed with research teams on a rotational basis and transfer ownership.
• Work directly in research codebases to improve reliability and structure.
• Anticipate silent failure modes and prevent them structurally via typing and testing.
• Contribute to reliability and triage tooling for production RL systems.
• Help define engineering standards, review practices, and design patterns for a new team.
• Demonstrate deep Python expertise, including typing and async patterns.
• Show a track record designing intuitive, safe APIs or frameworks.
• Experience working in large, evolving codebases you didn’t write initially.
• Anticipate failure modes and prevent them via system design and testing.
• Strong written and verbal communication skills for collaboration.
• Comfort with ambiguity and driving outcomes from loosely defined problems.

Skills

Python

API design

Framework design

Education

Bachelor's degree

Job description

Anthropic is seeking an experienced engineer to shape reinforcement learning tooling and APIs for agentic coding environments. You will embed with research teams, design frameworks, and maintain production RL runs. Strong Python, API design, and the ability to work in large codebases are essential.

Location-based hybrid policy requires in-office presence at least 25% of the time. You’ll collaborate across engineers and researchers, translating research needs into robust, scalable software that