LiftmyCVLiftmyCV
PI

Research Engineer - RL Infrastructure

Prime IntellectHybridSan Francisco, US
AI job summary

Prime Intellect seeks a Research Engineer to build systems infrastructure for large-scale reinforcement learning (RL) training. The position involves optimizing performance, improving memory and communication efficiency, and enabling efficient distributed workloads. Ideal candidates have experience in AI/ML infrastructure, particularly in large-scale model training and optimization techniques. The role offers flexible work arrangements, competitive compensation, and an opportunity to work on groundbreaking infrastructure for open superintelligence.

Job description

Building Open Superintelligence Infrastructure

Prime Intellect is building the open superintelligence stack: from frontier agentic models to the infrastructure that enables anyone to train, adapt, and deploy them. We unify globally distributed compute into a single control plane and pair it with the full reinforcement learning post-training stack: environments, secure sandboxes, verifiable evaluations, and our async RL trainer. We enable researchers, startups, and enterprises to run end-to-end RL at frontier scale, adapting models to real tools, workflows, and deployment environments. We are looking for a Research Engineer to work on the systems layer behind large-scale RL training. This role is for someone who enjoys going deep on performance: optimizing kernels, improving memory and communication efficiency, scaling distributed workloads, and pushing the throughput and reliability of training systems closer to hardware limits. If you care about making large-scale model training faster, cheaper, and more robust, we’d love to talk.

What You’ll Work On

  • Build and optimize the systems infrastructure behind large-scale RL and distributed training workloads.
  • Improve end-to-end training efficiency across compute, memory, networking, and scheduling layers.
  • Design and implement low-level performance optimizations, including kernels, communication paths, and runtime improvements.
  • Work on distributed training systems spanning data, tensor, and pipeline parallel workloads.
  • Help shape the architecture of our RL training stack, including async rollout and post-training systems.
  • Contribute to open-source libraries and internal infrastructure used for frontier-scale model training.
  • Collaborate closely with researchers and infrastructure engineers to translate bottlenecks into concrete systems improvements.
  • Stay at the frontier of training systems, inference systems, compiler/runtime tooling, and hardware-aware optimization techniques.

You May Be a Fit If You Have

  • Strong systems engineering experience in AI/ML infrastructure, especially around large-scale model training or inference.
  • Deep familiarity with PyTorch and distributed training frameworks such as PyTorch Distributed, DeepSpeed, FSDP, Megatron, vLLM, Ray, or related tooling.
  • Experience optimizing training performance across kernels, memory movement, communication overhead, or parallelization strategy.
  • Hands-on experience with large-scale training techniques including data parallelism, tensor parallelism, and pipeline parallelism.
  • Strong understanding of GPU architecture, profiling, and performance debugging.
  • Ability to identify bottlenecks across the stack and drive improvements from first principles.
  • Comfort working in a fast-moving environment with ambiguous problems and high ownership.

Especially Exciting

  • Experience writing or optimizing CUDA / Triton kernels.
  • Experience with compiler or runtime optimization for ML systems.
  • Experience working on RL training infrastructure, rollout systems, or asynchronous training pipelines.
  • Experience with multi-node GPU clusters and high-performance networking.
  • Contributions to open-source ML systems or infrastructure projects.
  • Interest in publishing technical work or sharing insights through engineering blogs and technical writing.

Why This Role Matters

The next frontier in AI will not be unlocked by models alone. It will be unlocked by systems that let those models train faster, adapt continuously, and operate across real environments at scale. That infrastructure does not exist yet in the form the world needs. We’re building it.

Benefits & Perks

  • Competitive compensation, including equity.
  • Flexible work arrangements, with the option to work remotely or in person from our San Francisco office.
  • Visa sponsorship and relocation support for international candidates.
  • Quarterly team offsites, hackathons, conferences, and learning opportunities.
  • A deeply technical, high-agency team working on infrastructure for open superintelligence.

If you’re excited about building the systems foundation for frontier-scale RL and open superintelligence, we’d love to hear from you.

Job details

Published
March 27, 2026
Job source
ashby
Workplace
Hybrid · San Francisco, US
First seen
March 27, 2026
AI match explained

See how well you match this job

Log in or sign up and Eva will compare your profile with this role, explain your strengths and show what to improve.

Sign up to see your matchAlready have an account? Log in

Visa sponsorship insights

Visa sponsorship available

This job posting states that visa sponsorship is available for qualified candidates.

More at Prime Intellect

Similar jobs from this company

None listed.

Across the market

Similar jobs from other companies

Third-party content disclaimer

Full job descriptions are sourced directly from third-party applicant tracking systems (ATS), job boards, recruitment platforms, and employer career pages.

LiftmyCV does not claim ownership of this content or guarantee its accuracy or current availability. All original content is the intellectual property of the respective employers or other rights holders.

LiftmyCV hiring intelligence, availability checks, and related-job recommendations are generated from LiftmyCV data and public sources.

If you prefer, you may apply directly via the original listing for transparency.