P

Research Engineer/Scientist, Reinforcement Learning

Prime Intellect • United State
Remote Visa Sponsorship Relocation
Apply Now
AI Summary

Develop algorithms and systems to train open superintelligence models using reinforcement learning. Focus on RL methods for reasoning, scaling science, and improving distributed training frameworks. Requires deep expertise in RL algorithms, PyTorch, and distributed ML systems.

Key Highlights
Develop RL methods for reasoning, coding, and long-horizon tasks
Design scaling experiments to optimize model size and training compute
Extend the prime-rl framework to support asynchronous training workflows

Looking to advance your Development & Programming career with relocation support? Explore Development & Programming Jobs with Relocation Packages that include comprehensive packages to help you move and settle in your new role.

Key Responsibilities
Develop and test RL methods for reasoning, coding, and long-horizon tasks, including changes to training objectives and policy optimization.
Investigate stability in asynchronous RL, including policy staleness and trainer/sampler mismatch.
Collaborate with data and evaluation researchers to understand the impact of task selection and rewards on model learning.
Design experiments to understand how RL performance changes with model size, training compute, and task horizon.
Turn experimental findings into training recipes and test them across larger models.
Extend prime-rl to support new algorithms, models, and asynchronous training workflows.
Improve performance and numerical correctness of research runs across trainers and rollout workers.
Build diagnostics to make unstable runs and performance regressions easier to reproduce.
Technical Skills Required
Python PyTorch Reinforcement Learning

Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.

Benefits & Perks
Cash Compensation Range of $150-350k
Equity incentives
Flexible work arrangements
Visa sponsorship
Relocation assistance
Quarterly team off-sites, hackathons, and conferences

Interested in relocating to United State? Check out our comprehensive Relocation Jobs in United State page with detailed relocation packages and benefits.

Nice to Have
Experience with distributed training frameworks or asynchronous rollout pipelines
Experience diagnosing unstable RL runs, including policy-staleness or numerical issues
Work on coding agents, verifiable rewards, or long-horizon environments

Job Description

Prime Intellect is building the open superintelligence stack: the infrastructure frontier AI labs build internally, made available to every ambitious AI team.
Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

Apply Now
See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources
Job Overview
Posted Date Oct 16, 2026
Employment Type Full-time
Experience Level Not Applicable
Location United State
Category Programming
Company Prime Intellect
Mentioned Skills
python ai cloudflare san datadog pytorch

Similar Jobs

Explore other opportunities that match your interests

Senior Rust Software Engineer (Embedded Systems) - Mission-Critical Solutions

Programming
•
7m ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

L3Harris Technologies

United State

Senior AI Engineer - Intelligent Foundations and Experiences

Programming
•
7m ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

Capital One

United State

Research Engineer – Large Language Model Pretraining
Programming
•
8m ago
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Not Applicable

Prime Intellect

United State

Subscribe our newsletter

New Things Will Always Update Regularly