Frontier AI Research Intern (RLVR & Data)

mercor; San Francisco (CA); On-site; USD 17,000 - 20,000; Full time

Benefits offered by this job

Mentorship from experienced researcher

Meal stipend $1.5K monthly for meals

Laundry reimbursement $200 monthly

Wellness reimbursement $200 monthly

Equinox membership

Team events and offsites

Potential full-time return offer

Job summary

Mercor’s Research Scientist Intern role focuses on frontier research in RLVR, data generation, and model evaluation. You will design controlled experiments to explore how datasets and training methods impact large language models, and collaborate with researchers to turn open questions into rigorous studies.

You’ll work with research scientists, engineers, and domain experts to advance Mercor’s agenda, potentially contributing to publications, benchmarks, and frontier AI systems.

Qualifications

• Demonstrated ability to formulate research questions, design experiments, and draw sound conclusions from empirical results.
• Experience training, fine‑tuning, or evaluating language models.
• Familiarity with RL environments, reward modeling, or agentic AI systems.
• 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 and ownership in a fast-paced research environment.

Responsibilities

• Develop and investigate research questions related to post‑training, RLVR, data quality, and model evaluation.
• Design and run controlled experiments to understand how datasets, rewards, and training strategies affect model performance.
• Study reward‑shaping and post‑training methods, including approaches such as 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 opportunities for improvement.
• Analyze experimental results and communicate findings through clear reports, research artifacts, and presentations.
• Build the research tooling and data pipelines needed to conduct experiments at scale.
• Collaborate with research scientists, research engineers, applied AI teams, and domain experts producing training and evaluation data.
• Contribute to research publications, benchmark releases, and other public research outputs where appropriate.

Skills

Research design

Python programming

Empirical analysis

Publications or OSS

RL environments

Language models evaluation

Intellectual curiosity

Fast-paced environment

Education

Master's or PhD in CS/ML/Statistics

Tools

Python

Job description

Mercor’s Research Scientist Intern role focuses on frontier research in RLVR, data generation, and model evaluation. You will design controlled experiments to explore how datasets and training methods impact large language models, and collaborate with researchers to turn open questions into rigorous studies.

You’ll work with research scientists, engineers, and domain experts to advance Mercor’s agenda, potentially contributing to publications, benchmarks, and frontier AI systems.