Latest AI JobsBrowse Jobs
mercor logo

Research Scientist - Environments, Data and Post-Training

mercorSan FranciscoResearch
Apply on company site
Salary
$250K – $500K
Job type
Full-time
Experience
Senior
Posted
18 Sept 2026
Status
Open · checked 7d ago

About this role

Mercor seeks a Research Engineer for Environments, Data and Post-Training in San Francisco to drive frontier model development through scalable experiments and infrastructure. This full-time, in-person position suits professionals with a strong background in machine learning training, reinforcement learning, and post-training research.

Role Overview

Mercor is hiring a Research Engineer for its San Francisco office to focus on frontier post-training, data, and environments. The professional in this role will design and execute experiments across datasets, rewards, and optimization strategies to improve model capabilities. The position requires working in person five days a week and collaborating closely with researchers, engineers, and domain experts.

Key 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.

Requirements

Demonstrated experience training and evaluating machine learning models.
A 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.
Availability to work in person in San Francisco, five days a week.

Nice to Have

Experience on an industry post-training or frontier-model team.
Main authorship of publications at top-tier conferences such as NeurIPS, ICML, and ACL.
Experience with synthetic-data generation.
Experience building large-scale evaluation or data-generation infrastructure.
Solid foundations in distributed or backend systems, and experimental design.
Familiarity with APIs, databases, and cloud infrastructure.

Skills and Tools

Reinforcement Learning with Verifiable Rewards (RLVR)
GRPO
DAPO
Distributed and backend systems
APIs, databases, and cloud infrastructure

Salary and Benefits

Salary range of $250,000 to $500,000
Offers equity with a generous grant vested over 4 years
Bi-annual performance bonus structure
Up to $15,000 relocation bonus
$10,000 housing bonus for living within 0.5 miles of the office
$1,500 monthly meal stipend
Free Equinox membership
$200 monthly laundry reimbursement
$200 monthly personal wellness reimbursement
Health, dental, and vision insurance

About the Company

Mercor is an AI data company and a profitable Series C enterprise valued at $10 billion. The organization builds the layer between human expertise and frontier models, paying millions of domain experts to train AI systems. Its offerings include the APEX benchmark family and Mercor Enterprise, which helps Fortune 500 companies translate human expertise directly into agents. The team works in person five days a week across offices in San Francisco, New York City, and London.

How to Apply

To apply for this position, please visit the official company careers page.

Skills and tech stack

GRPODAPORLVRReinforcement LearningMachine Learning

Questions candidates ask

Where is the job located?

The role is based in San Francisco and requires working in person five days a week.

What is the salary and compensation structure?

The salary ranges from $250K to $500K, and includes equity, a bi-annual performance bonus structure, and various stipends and allowances.

What qualifications are required for the role?

Candidates need demonstrated experience training and evaluating machine learning models, a strong research record in post-training or reinforcement learning, strong programming skills, knowledge of the current AI research landscape, and the ability to work in person in San Francisco.

What optimization methods are mentioned in the posting?

The posting mentions methods such as GRPO and DAPO.

What are some of the additional employee benefits offered?

Benefits include a $15k relocation bonus, a $10k housing bonus for living close to the office, a $1.5k monthly meal stipend, a free Equinox membership, monthly wellness and laundry reimbursements, and health, dental, and vision insurance.

Ready to apply?

The application is on the official mercor careers page.

Apply on company site