Frontier Post-Training Research Engineer

Apply; San Francisco, Northern (CA, KY); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Bi-annual bonus

Equity grant

Relocation bonus

Housing bonus

Meals stipend

Equinox membership

Laundry reimbursement

Wellness reimbursement

Health insurance

Job summary

Mercor is hiring a Research Scientist to work at the intersection of research and engineering on frontier post-training. You will develop new training and evaluation methods, test them through experiments, and implement successful approaches at scale.

You will collaborate with researchers, engineers, and domain experts to explore how data, rewards, environments, and optimization shape model behavior, influencing Mercor’s products and open research.

Qualifications

• Demonstrated experience training and evaluating machine learning models.
• Strong research record in post-training, reinforcement learning, language-model evaluation, data-centric ML, or a closely related field.
• Ability to reason rigorously about model behavior, experimental results, and data quality.
• Strong programming skills and experience implementing machine learning systems.
• Knowledge of the current AI research landscape and important open problems.
• Excitement to work in person in San Francisco, five days a week (with optional remote Saturdays).

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.
• 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.

Skills

ML research

Reinforcement learning

Experiment design

Programming

Tools

APIs

Cloud infrastructure

Databases

Job description

Mercor is hiring a Research Scientist to work at the intersection of research and engineering on frontier post-training. You will develop new training and evaluation methods, test them through experiments, and implement successful approaches at scale.

You will collaborate with researchers, engineers, and domain experts to explore how data, rewards, environments, and optimization shape model behavior, influencing Mercor’s products and open research.