Research Engineer, Intern – Benchmarking

About Mercor Mercor’s mission is to organize human intelligence for the AI economy. We build the infrastructure that enables frontier AI labs and enterprises to train, evaluate, and improve AI on real-world professional work. More than five million experts have joined our network, and we pay out over $5 million daily for their knowledge and expertise. We built our training and evaluation infrastructure alongside the world’s leading AI labs. Now, we’re bringing those capabilities to enterprises across industries, enabling them to train, evaluate, and improve AI using their own expertise and standards. Our APEX benchmarks measure how AI performs on economically valuable work, while our enterprise evaluations and post-training capabilities turn those insights into measurable improvements across real-world workflows. Our work sits at the intersection of frontier AI, human expertise, and real-world application. We’re solving problems few companies have encountered, with the opportunity to influence what the world’s most advanced AI systems become capable of doing. We’re looking for people who bring different perspectives, take ownership, exercise sound judgment, and hold themselves to an exceptionally high standard. You’ll have the opportunity to do consequential work alongside talented colleagues who challenge one another, collaborate openly, and share a commitment to excellence. Mercor is profitable and recently raised a $750 million Series D at a $20 billion valuation. We work in person five days a week in San Francisco, New York, and London. About the Role As a Research Engineer at Mercor, you’ll work at the intersection of engineering and applied AI research. You’ll own benchmarking pipelines, evaluation systems, and failure analysis workflows that directly inform how we train and improve frontier language models. Your work will define how we measure tool use, agentic behavior, and real-world reasoning. You’ll design and run evals, build rubrics and scorers, and turn failure analysis into actionable improvements for post-training, RLVR, and data pipelines. What You’ll Do Benchmarking: Design, implement, and maintain benchmarks and metrics for tool use, agentic behavior, and real-world reasoning; ensure benchmarks scale with training and stay aligned with product and research goals. Evaluation systems: Build and operate LLM evaluation systems end-to-end runs, scoring, dashboards, and reporting, so researchers and applied AI teams can track model performance and compare runs at scale. Failure analysis: Run systematic failure analysis on model outputs (e.g., wrong tool use, reasoning errors, safety/alignment issues); categorize failure modes, quantify prevalence, and feed findings into reward design, data curation, and benchmark design. Rubrics and evaluators: Create and refine rubrics, automated evaluators, and scoring frameworks that drive training and evaluation decisions; balance rigor with scalability (human vs. model-as-judge, calibration, agreement). Data quality and usability: Quantify data usability, quality, and impact on key benchmarks; use evals and failure analysis to guide data generation, augmentation, and curation. Cross-team collaboration: Work with AI researchers, applied AI teams, and data producers to align evals with training objectives and to prioritize benchmarks and failure analyses that matter most. Ownership in a fast-paced environment: Operate in a high-iteration research setting with strong ownership of benchmarks, evals, and failure-analysis workflows. What We’re Looking For Strong applied research background, with 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. Excitement to work in person in San Francisco five days a week in a high-intensity, high-ownership environment. Nice To Have Industry experience on a post-training or evaluation/benchmarking team (highest priority). Publications at top-tier venues (NeurIPS, ICML, ACL), especially in evaluation or benchmarking. Experience building or running LLM evaluations, benchmarks, or failure-analysis pipelines. Experience with synthetic data generation, rubric design, or RL-style workflows that use evals for reward shaping. Work samples or code (e.g., eval frameworks, benchmark suites, failure-analysis reports or tooling) that demonstrate relevant skills. Benefits Health Benefits eligible at 30+ hours a week Overtime eligible at 1.5x from 40 to 55 hours; 2x over 55 hours-week. $1.5K monthly stipend for meals Relocation & Housing Support Free Equinox membership $200 monthly laundry reimbursement $200 monthly personal wellness reimbursement Mercor is an Equal Opportunity Employer and is committed to providing equal opportunity to all employees and applicants. Mercor does not discriminate based on actual or perceived race, color, creed, religion, national origin, ancestry, citizenship status, age, sex or gender (including pregnancy, childbirth, related medical conditions and lactation), gender identity or gender expression, sexual orientation, marital status, military service and veteran status, disability, protected medical condition as defined by California or local law, genetic information, or any other characteristic protected by applicable federal, California, or local laws and ordinances. Further, Mercor prohibits discrimination, harassment, and retaliation based on any combination of protected characteristics. This Policy applies to all areas of employment, including recruitment, hiring, training, promotion, compensation, benefits, discipline, termination, and all other privileges, terms, and conditions of employment. This Policy and the law prohibit employment discrimination against any employee or applicant based on any legally protected status.