Research Engineer, Intern – Benchmarking
San Francisco • Intern
Posted 1d ago
About the job
Mercor is seeking a Research Engineer Intern to work at the intersection of engineering and applied AI research. This role will focus on owning benchmarking pipelines, evaluation systems, and failure analysis workflows that directly inform how we train and improve frontier language models. Your work will be crucial in defining how we measure tool use, agentic behavior, and real-world reasoning. You will design and run evaluations, build rubrics and scorers, and translate failure analysis into actionable improvements for post-training, RLVR, and data pipelines.
Responsibilities
- Design, implement, and maintain benchmarks and metrics for tool use, agentic behavior, and real-world reasoning.
- Build and operate LLM evaluation systems, including end-to-end runs, scoring, dashboards, and reporting.
- Perform systematic failure analysis on model outputs, categorize failure modes, and quantify prevalence.
- Create and refine rubrics, automated evaluators, and scoring frameworks.
- Quantify data usability, quality, and impact on key benchmarks.
- Collaborate with AI researchers, applied AI teams, and data producers to align evaluations with training objectives.
- Operate in a high-iteration research setting with strong ownership of benchmarks, evaluations, and failure-analysis workflows.
Requirements
- Strong applied research background with a focus on model evaluation, benchmarking, and/or failure analysis.
- Strong coding skills and hands-on experience with ML models and evaluation code.
- Solid grasp of data structures, algorithms, and backend systems.
- Comfort with APIs, SQL/NoSQL, and cloud platforms for running and storing eval results.
- Ability to reason about model behavior, experimental results, and data quality from evals and failure analyses.
Benefits
- $1.5K monthly stipend for meals
- Free Equinox membership
- $200 monthly laundry reimbursement
- $200 monthly personal wellness reimbursement