Research Engineer, Takeoff Intel
Core
Build and run evaluation and measurement instruments to track AI R&D capabilities and model development recursion.
Role type
Research Engineer (AI Evaluation & Measurement)
Builds
Evaluation harnesses, data pipelines, and analysis tooling for AI capability assessments
Domain
Artificial Intelligence, AI Safety, Model Evaluation
Deliverable
production ML models | dashboards & analysis
Required skills
LLM experimentation, large-scale data processing, rapid prototyping, evaluation design, code review of AI-generated code, quantitative analysis
Preferred skills
LLM benchmark infrastructure, large-scale ML/data infrastructure, research library development, debugging AI-written code
Technologies
Large Language Models, data pipelines, evaluation frameworks
Responsibilities
Design and run capability evaluations at scale, build data pipelines for telemetry metrics, prototype and validate new instruments, review AI-written code, collaborate with researchers on measurement definitions
Seniority
Junior to Senior
