About this role
Join a small, technical team focused on building benchmarks to rigorously evaluate frontier AI agents on realistic, domain-specific workflows. You will own the design and implementation of these benchmarks, ensuring their credibility and relevance to real-world performance. This role offers the opportunity to shape the future of AI agent evaluation.
What we are looking for 6
- Design, implement, and maintain AI agent benchmarks
- Translate real-world workflows into evaluation tasks
- Build scalable infrastructure for running AI agents
- Develop metrics and analyses for benchmark validation
- 2+ years in research engineering or ML engineering
- Proficiency in Python, Docker, and Linux