AfterQuery
Research Scientist – Frontier Evaluations
$210K–$450K
San Francisco · On-site · Full-time · Posted Sep 10, 2026
- Education
- PhD in a related technical field (preferred).
About the job
Designs and publishes rigorous evaluations of frontier AI systems, from benchmark development through analysis and public research.
What you'll do
- Lead the design, validation, launch, and improvement of frontier AI benchmarks; build reproducible evaluation systems.
- Work with researchers and domain experts to evaluate model capabilities and failure modes, and collaborate on post-training and performance measurement.
- Communicate findings through benchmark reports, technical articles, and research papers.
What they ask for
- Strong record of publishing benchmarks or research papers.
- Clear technical communication and strong scientific writing skills; commitment to rigorous experimental methods.
- Ability to take an ambiguous evaluation question from scoping through reproducible public release.
- Depth in agentic, coding, and safety evaluations or applied machine learning in an expert domain.
Nice to have
- PhD in a related technical field.
- Research publications at leading conferences or peer-reviewed journals.
Pay
$210K – $450K (base salary)
AI focus
Develops and studies evaluations for frontier AI, including agentic, coding, safety, and expert-domain systems; collaborates on post-training and measures performance gains.
Model-written summary · the original posting is authoritative