Full-Stack Software Engineer, Reinforcement Learning

Highlights

• Build platforms powering RL environment creation and training observability.
• Build evaluation dashboards catching reward hacks in real time.
• Scale human data collection to distill thousands of experts into Claude.

What they offer

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space for collaboration

Ideal candidate

High-agency full-stack builder who thrives in fast, ambiguous loops and cares about intuitive UX. Motivated by Anthropic's mission to build safe, beneficial AI and turn expert knowledge into better models.

Requirements

• Strong software engineering fundamentals with full-stack range from database to frontend
• Proficient in Python and a modern web stack like React, TypeScript or similar
• Track record of shipping systems that solved hard problems
• Operate with high agency without waiting for a ticket
• Care about UX for technical researchers and non-technical labelers
• Communicate clearly and turn vague asks into well-scoped work
• Bachelor's degree or equivalent combination of education, training and experience