You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Prime Intellect

Research Engineer / Scientist - Reinforcement Learning

  • Hybrid

Salary

$150,000 - 350,000/ year

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company builds the infrastructure that large AI labs usually keep in-house, and makes it available to AI teams of any size.

The platform brings compute, environments, evaluations, secure sandboxes, fast training and deployment into one system for post-training at large scale, covering SFT, RL, tool use, agent workflows and production models that keep improving.

The company trains open models end to end on long-horizon tasks such as autonomous research, and its research team uses the platform to do this.

The company has raised $150M in total funding from investors including Founders Fund, Radical Ventures and NVIDIA.

The role centers on the algorithms and systems used to train the company's open models with RL. Hiring covers RL algorithms, scaling research and training frameworks, and you can focus on whichever fits your strengths.

Responsibilities

  • Research RL methods for reasoning, coding and long-horizon work, including new training objectives and policy optimization.
  • Study instability in asynchronous RL, such as stale policies, gaps between trainer and sampler, and numerical differences between training and rollouts.
  • Partner with data and evaluation researchers to see how task selection, rewards and training data shape what the model learns.
  • Run controlled experiments on how RL performance and learning dynamics change with model size, training compute and task horizon.
  • Use ablations and evaluations to separate real learning gains from reward exploitation, evaluation artifacts and training bugs.
  • Turn findings into training recipes and check whether the gains hold for larger models and longer runs.
  • Add support for new algorithms, models and asynchronous training workflows to the in-house RL framework.
  • Improve speed and numerical correctness of research runs across trainers, rollout workers and environments, working with the infrastructure team.
  • Build diagnostics that make unstable runs and regressions easy to reproduce, and tell algorithm problems apart from implementation or runtime issues.

Requirements

  • Deep experience in at least one of RL algorithms, empirical model training research or distributed ML systems, shown through research, open-source work or systems you have built.
  • Strong Python skills and experience with PyTorch or a comparable ML framework.
  • Ability to design controlled experiments, interpret results and debug unexpected model or system behavior.
  • Experience taking a research idea or systems change through implementation, testing and evaluation, and being able to say what worked and what did not.
  • Experience with distributed training frameworks or asynchronous rollout pipelines.
  • Experience diagnosing unstable RL runs, including policy staleness or numerical issues.
  • Experience with coding agents, verifiable rewards or long-horizon environments.

Conditions

You can work remotely or in person at the San Francisco office.

Benefits

  • Cash compensation of $150-350k, plus equity incentives tied to the company's growth.
  • Full medical, dental and vision coverage for employees and dependents.
  • Flexible PTO.
  • $200/month health and wellness benefit.
  • Visa sponsorship and relocation assistance for international candidates.
  • Budget for professional development, including courses and conferences.
  • Quarterly team off-sites, hackathons, conferences and learning opportunities.
  • Meals covered when working from the San Francisco office.

Where you’d work

Part of the week in the office

You can work from

  • United States

Relocation offered

Visa sponsored

About the company

Prime Intellect

  • Industry: AI

Also hiring in San Francisco, United States

2 of their 11 open roles are remote

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 23 checks run
  • 6 red flags

Still hiring?

14 checks

2 red flags

How crowded?

9 checks

4 red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details13 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • Python
  • PyTorch
  • LangChain
  • Databricks
Type
Full-time
Equity
Equity offered
Industry
AI
Specialty
ML
Region
United States
Show 7 more factsShow less

Role

Category
Data & Analytics
Specialty
ML
Tech stack
  • Python
  • PyTorch
  • LangChain
  • Databricks

Location

Work model
Hybrid
Region
United States
Remote from
  • United States
Relocation
Offered
Visa sponsorship
Sponsored

Compensation

Salary
$150,000 - 350,000 / year
Pay period
Annual
Equity
Equity offered

Employment

Type
Full-time

Company

Industry
AI

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason