Mid-Level Research Engineer, Benchmarks
Core
Design, implement, and maintain benchmarks for evaluating frontier AI agents on domain-specific tasks and realistic workflows.
Role type
Mid-level research engineer (AI evaluation infrastructure)
Builds
Benchmarks and evaluation infrastructure for AI agents
Domain
Artificial Intelligence / Machine Learning / Evaluation
Deliverable
production ML models
Required skills
Python, Docker, Linux, benchmark design, infrastructure scaling, metrics development, technical writing
Preferred skills
Reinforcement learning pipelines, data generation, published work, public benchmarks
Responsibilities
Design and implement benchmarks for frontier AI agents; Collaborate with subject-matter experts to define tasks and criteria; Build infrastructure to run models and agents at scale; Develop metrics to assess benchmark quality; Validate benchmark results against real-world needs; Write technical documentation and reports
Seniority
Mid-level, hands-on IC
