Research Intern
San Francisco • Intern
Posted 6h ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
Intern
Categories
AI Research Engineer
About the job
As a Research Scientist Intern at Mercor, you will contribute to cutting-edge research in areas such as post-training, reinforcement learning with verifiable rewards (RLVR), data generation, and model evaluation. You will investigate the impact of datasets, rewards, and training methods on large language models' capabilities and behavior. This role involves designing experiments, developing new evaluation methodologies, conducting failure analysis, and testing approaches to enhance tool use, agentic behavior, and real-world reasoning. You will collaborate closely with research scientists, engineers, and domain experts to transform open-ended questions into rigorous experiments, contributing to Mercor's research agenda and potentially supporting external publications and the development of advanced AI systems.
Responsibilities
- Develop and investigate research questions in post-training, RLVR, data quality, and model evaluation.
- Design and execute controlled experiments to understand the influence of datasets, rewards, and training strategies on model performance.
- Study reward-shaping and post-training methods, including GRPO and DAPO.
- Develop methods for measuring data quality, usability, and performance uplift on key benchmarks.
- Design and evaluate datasets, rubrics, evaluators, and scoring frameworks for complex model capabilities.
- Conduct systematic error analysis to identify model failure modes and improvement opportunities.
- Analyze experimental results and communicate findings through reports, research artifacts, and presentations.
- Build research tooling and data pipelines for large-scale experiments.
- Collaborate with research scientists, engineers, applied AI teams, and domain experts on training and evaluation data.
- Contribute to research publications, benchmark releases, and other public research outputs.
Requirements
- Currently pursuing a master's or PhD in computer science, machine learning, statistics, mathematics, or a related field.
- Demonstrated ability to formulate research questions, design experiments, and draw sound conclusions from empirical results.
- Experience in at least one of the following: training, fine-tuning, or evaluating language models; agentic AI systems or RL environments; developing benchmarks, evaluation methodologies, or data-quality measures.
- At least one publication or open-source project.
- Strong programming skills, particularly in Python, and the ability to write reliable research code.
- Familiarity with machine learning fundamentals, experimental design, and statistical analysis.
- Intellectual curiosity.
- Comfort operating in a fast-paced research environment with rapid iteration and a high degree of ownership.
Benefits
- Mentorship from experienced researchers.
- Work on real, high-impact projects.
- $1.5K monthly stipend for meals
- $200 monthly laundry reimbursement
- $200 monthly personal wellness reimbursement
- Free Equinox membership
- Team events and offsites.
- Potential full-time return offer.