Intelligence
Member of Technical Staff, Frontier Evals
San Francisco · On-site · Staff · Full-time · Posted Aug 3, 2026
- Education
- Studied Computer Science, Data Science, Statistics, Math, Engineering, Physics, or a related field.
- Visa sponsorship
- The company sponsors visas and handles relocation.
About the job
Develop benchmarks and evaluation methods for frontier AI models, investigate model behavior, and publish research and analyses that inform industry evaluation.
What you'll do
- Design challenging, useful evaluations of frontier models on real-world tasks.
- Investigate model failures and what they reveal about emerging capabilities.
- Publish research, technical reports, and analyses on frontier-model evaluation.
What they ask for
- Strong STEM background in Computer Science, Data Science, Statistics, Math, Engineering, Physics, or a related field.
- Deep curiosity about frontier AI models and understanding model behavior.
- Intellectual drive to work at the frontier of AI development.
- Willingness to do hands-on work.
AI focus
Evaluating frontier AI models by designing benchmarks, running experiments, analyzing model behavior and failures, and developing evaluation methodologies.
Model-written summary · the original posting is authoritative