Post-Training Research Engineer, Environments & Data

AI Chopping Block; San Francisco, Northern (CA, KY); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Bi-annual performance bonus

Generous equity grant

Relocation bonus up to $15k

Housing bonus up to $10k

Meal stipend $1.5k monthly

Equinox membership

Laundry reimbursement $200/mo

Wellness reimbursement $200/mo

Health, Dental, Vision insurance

Job summary

Mercor in San Francisco is seeking a Research Scientist to bridge research and engineering on frontier post-training methods. You will design experiments, test new training recipes, and scale successful approaches across data, rewards, and environments.

You will collaborate with researchers, engineers, and domain experts, publishing findings through blog posts, reports, and papers while contributing to open-source post-training tools.

Qualifications

• Proven experience training and evaluating machine learning models.
• Strong research track record in ML, RL, or data-centric ML.
• Ability to reason about model behavior and data quality.
• Strong programming skills with ML systems experience.

Responsibilities

• Implement novel post-training methods that improve model reasoning, tool use, and agentic behavior.
• Develop new training recipes for frontier open models.
• Design and run experiments across datasets, reward functions, environments, and optimization strategies, including methods such as GRPO and DAPO.
• Build reinforcement learning with verifiable rewards (RLVR) and other post-training pipelines at scale.
• Investigate model capabilities and failure modes, then develop targeted training interventions.
• Create methods for measuring data quality, usability, and causal impact on model performance.
• Build scalable pipelines for data generation, filtering, augmentation, and selection.
• Develop rubrics, evaluators, benchmarks, and scoring systems that inform training decisions.
• Translate open-ended research questions into rigorous experiments and production systems.
• Collaborate with researchers, applied AI teams, engineers, and domain experts producing training data.
• Contribute to open-source post-training tools and research.

Job description

Mercor in San Francisco is seeking a Research Scientist to bridge research and engineering on frontier post-training methods. You will design experiments, test new training recipes, and scale successful approaches across data, rewards, and environments.

You will collaborate with researchers, engineers, and domain experts, publishing findings through blog posts, reports, and papers while contributing to open-source post-training tools.