Member of Technical Staff (Applied AI Research)
Core
Design and ship novel evaluation methodologies, datasets, and scoring systems to benchmark frontier AI models for labs, enterprises, and policymakers.
Role type
Senior IC applied AI research engineer (benchmarking)
Builds
Novel AI evaluation benchmarks, datasets, and analysis reports
Domain
Artificial Intelligence / Benchmarking
Deliverable
production ML models
Required skills
Python, data analysis, critical thinking, modern AI systems knowledge, coding
Preferred skills
Experience with frontier AI models, ability to work with pre-release models, strong analytical frameworks
Technologies
Python, data analysis tools
Responsibilities
Design frontier evaluation methodologies, construct evaluation datasets and infrastructure, run evaluation suites across major model releases, publish influential analysis reports, benchmark pre-release models with frontier labs
Seniority
Senior, hands-on IC