---
title: 'Research Engineer / Scientist - Reinforcement Learning at Prime Intellect'
canonical: 'https://feeny.ai/job/research-engineer-scientist-reinforcement-learning-prime-intellect-san-francisco-14pw1t4w47jd'
type: 'job'
last_seen: '2026-10-19'
---

# Research Engineer / Scientist - Reinforcement Learning at Prime Intellect

- **Company:** Prime Intellect
- **Location:** San Francisco, CA
- **Employment:** full-time
- **Posted:** 2026-10-16
- **Last confirmed live:** 2026-10-19
- **Apply:** https://jobs.ashbyhq.com/primeintellect/7bd4beca-6c73-4a38-9a6b-09dfa855dcf0

## Job description

Own Your Intelligence

Prime Intellect is building the open superintelligence stack: the infrastructure frontier AI labs build internally, made available to every ambitious AI team.

Our platform, Lab, unifies compute, environments, evaluations, secure sandboxes, high-performance training, and deployment into one full-stack system for post-training at frontier scale - from SFT and RL to tool use, agent workflows, and continuously improving production models. We are building open frontier AI: open-source models trained end to end for long-horizon tasks like autonomous research, and the full-stack platform our own research team uses to build them. The next generation of AI companies, enterprises, and research teams do not just need more GPUs. They need the ability to turn their own workflows, tools, data, and feedback loops into superintelligence they own.

Prime Intellect has raised $150M in total funding from Founders Fund, Radical Ventures, NVIDIA, and exceptional AI, infrastructure, and enterprise operators — including Andrej Karpathy, Dwarkesh Patel, and leaders and founders from Ramp, Perplexity, Harvey, Mercor, Zapier, Datadog, Cognition, OpenAI, Thinking Machines, Together AI, SemiAnalysis, LangChain, Browserbase, Cloudflare, Sierra, Databricks, Airbnb, OpenRouter, Standard Intelligence, Fleet, Core Auto, and more. We are looking for people who want to build at the intersection of frontier research, real infrastructure, and go-to-market for a category that does not fully exist yet.

## Role Impact

Help develop the algorithms and systems used to train Prime Intellect’s open models with reinforcement learning. We’re hiring research engineers and scientists across RL algorithms, scaling research, and training frameworks. Your focus will reflect your strengths; you don’t need to cover all three.

## Responsibilities

Algorithm research

- 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, trainer/sampler mismatch, and numerical differences between training and rollouts.
- Work with data and evaluation researchers to understand how task selection, rewards, and training data affect what the model learns.

Scaling science

- Design experiments to understand how RL performance and learning dynamics change with model size, training compute, and task horizon.
- Use controlled ablations and evaluations to distinguish learning gains from reward exploitation, evaluation artifacts, or training bugs.
- Turn experimental findings into training recipes, then test whether the improvements hold across larger models and longer runs.

RL frameworks

- Extend [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) to support new algorithms, models, and asynchronous training workflows.
- Improve the performance and numerical correctness of research runs across trainers, rollout workers, and environments, working with the infrastructure team.
- Build diagnostics that make unstable runs and performance regressions easier to reproduce, and help distinguish algorithm problems from implementation or runtime issues.

## Requirements

- Demonstrated depth in at least one of RL algorithms, empirical research on model training, or distributed ML systems. This could come through research, open-source contributions, or systems you’ve built.
- Strong programming skills in Python 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, with a clear account of what worked and what didn’t.

## 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.

## Benefits and Perks

- Cash Compensation Range of $150-350k, including equity incentives, aligning your success with the growth and impact of Prime Intellect.
- Flexible work arrangements, with the option to work remotely or in-person at our offices in San Francisco.
- Visa sponsorship and relocation assistance for international candidates.
- Quarterly team off-sites, hackathons, conferences and learning opportunities.
- Opportunity to work with a talented, hard-working and mission-driven team, united by a shared passion for leveraging technology to accelerate science and AI.

If you're excited about the opportunity to build the foundation for the future of decentralized AI and create a platform that empowers developers and researchers to push the boundaries of what's possible, we'd love to hear from you.

## About Prime Intellect

## Company Overview
- **One-liner**: Prime Intellect provides an open, full-stack platform for companies to train, deploy, and continuously improve their own AI models through large-scale distributed reinforcement learning.
- **Entity Type**: Private (Series B)
- **Headquarters**: San Francisco, California, United States
- **Founded**: 2023
- **Founders**: Vincent Weisser (CEO), Johannes Hagemann (CTO)

## Core Business
- **Primary industry**: AI infrastructure, open-source AI research, and agentic training platforms
- **Target customers**: B2B — enterprises and AI labs that want to train custom models without building their own infrastructure; also open-source community contributors
- **Mission**: Democratize frontier AI training by making it accessible to every company and collectively owning the resulting open innovations.

## Products & Services
- **Compute**: Access to GPU clusters (H100, H200, B200+) from 50+ providers, plus on-demand single GPU instances and reserved clusters with InfiniBand networking and SLURM/K8s orchestration.
- **Hosted Training (Lab)**: Managed large-scale reinforcement learning (RL) training without infrastructure overhead, including a 2,500+ environment hub and custom eval benchmarks.
- **Inference**: Serverless or dedicated inference for custom models, with native LoRA support and 1-click deployment.
- **Open-Source Libraries**: `prime-rl` (async RL framework), `verifiers` (environments & evals), and environment hub for collaborative development.
- **INTELLECT-3**: A 100B+ parameter Mixture-of-Experts model trained on their RL stack, achieving state-of-the-art performance for its size.

## Market Standing
- **Valuation/Market Cap**: Not publicly disclosed
- **Total Funding**: $70.44M across multiple rounds (CBInsights, 2026); earlier reports indicated $20.5M in seed rounds, followed by a Series B round of $49.94M led by Founders Fund and other investors.
- **Notable Investors/Partners**: Founders Fund, CoinFund, Distributed Global, Radical Ventures, Andrej Karpathy, Clem Delangue (Hugging Face), Dylan Patel (SemiAnalysis), Tri Dao (Together AI).
- **Growth Signals**: Headcount grew 128.6% YoY to 36 employees; 24 active job postings (monthly job growth +26.3%); launched INTELLECT-3 and SYNTHETIC-2 datasets; customers include Ramp and Zap; operates in 9 countries.

## Competitive Advantages
- **Full-stack integrated platform** – compute, post-training, evals, and inference in one place, reducing the fragmentation of building and maintaining AI workflows.
- **Large-scale distributed RL expertise** – proven ability to train 100B+ models across clusters (global training via their RL stack).
- **Open-source ethos** – models, datasets, and libraries are released openly, attracting a community of researchers and developers.
- **Founding team & research edge** – strong ties to frontier AI research, with contributions like prime-rl and self-improving agent loops.

## Strategic Focus
- **Self-improving agents** – building infrastructure that closes the loop from deployment back to training, enabling models to compound performance over time.
- **Scaling RL at extreme sizes** – recent research (RL at 1T Scale) shows commitment to massive-scale reinforcement learning.
- **Enterprise adoption** – adding dedicated solutions engineers and managed workflows for corporate customers.

## Why Work Here
- **Culture**: Seeks “the most ambitious developers” and emphasizes cutting-edge research and engineering. The team includes former engineers from Together AI, Aleph Alpha, and Anyscale.
- **Remote/Hybrid**: Remote-friendly with HQ in San Francisco.
- **Growth trajectory**: Rapidly scaling company (headcount up 128% YoY) with multiple open roles across engineering, research, and go-to-market.
- **Tech stack**: Python, PyTorch, CUDA, Kubernetes, SLURM, Grafana, and a broad modern AI toolchain – opportunity to work on infrastructure-level challenges.

## Sources
1. [primeintellect.ai](https://www.primeintellect.ai/)
2. [linkedin.com/company/primeintellect-ai](https://www.linkedin.com/company/primeintellect-ai)
3. [jobs.ashbyhq.com/PrimeIntellect](https://jobs.ashbyhq.com/primeintellect)
4. [cbinsights.com/company/prime-intellect](https://www.cbinsights.com/company/prime-intellect)
5. [docs.primeintellect.ai/introduction](https://docs.primeintellect.ai/introduction)

## Other roles at Prime Intellect

- [Research Engineer - RL Infrastructure](https://feeny.ai/job/research-engineer-rl-infrastructure-prime-intellect-san-francisco-faaejgnzefb8) — San Francisco, CA
- [Research Engineer - Pretraining Data](https://feeny.ai/job/research-engineer-pretraining-data-prime-intellect-san-francisco-fbgk1zsg5rfx) — San Francisco, CA
- [Research Engineer - Data and Evaluation](https://feeny.ai/job/research-engineer-data-and-evaluation-prime-intellect-san-francisco-pbeyv35k8888) — San Francisco, CA
- [Research Engineer - Pretraining](https://feeny.ai/job/research-engineer-pretraining-prime-intellect-san-francisco-zemr10qw9rtd) — San Francisco, CA
- [Research Engineer - Inference](https://feeny.ai/job/research-engineer-inference-prime-intellect-san-francisco-1rywfz5aktgb) — San Francisco, CA
- [Member of Technical Staff - Datacenter Networking](https://feeny.ai/job/member-of-technical-staff-datacenter-networking-prime-intellect-san-francisco-nad0z4zmmdmc) — San Francisco, CA
- [Member of Technical Staff - Storage Infrastructure](https://feeny.ai/job/member-of-technical-staff-storage-infrastructure-prime-intellect-san-francisco-039n2ahf9xzy) — San Francisco, CA
- [Product Marketing Lead](https://feeny.ai/job/product-marketing-lead-prime-intellect-san-francisco-qmet74zfdsaq) — San Francisco, CA
- [Strategic Account Executive - AI Infrastructure](https://feeny.ai/job/strategic-account-executive-ai-infrastructure-prime-intellect-san-francisco-hv0skjf5w6zy) — San Francisco, CA
- [Founding Solutions Architect](https://feeny.ai/job/founding-solutions-architect-prime-intellect-san-francisco-rrwa9hfn3xgq) — San Francisco, CA