Applied Research - Forward-Deployed
Prime Intellect builds the 'Open Superintelligence Stack' — an integrated compute, training, inference, and sandbox platform that lets companies train, deploy, and continuously improve their own AI models and agents. It serves AI startups, 'neolabs', and enterprises (over 6,000 customers, including Ramp and Zapier) that want to own their model optimization loop rather than rely solely on closed frontier labs.
Investors
Projects
About Prime Intellect
Prime Intellect is a San Francisco-based AI infrastructure company building what it calls the Open Superintelligence Stack: a full-stack platform spanning GPU compute (on-demand and reserved clusters), large-scale reinforcement learning training ('Lab'), an Environments Hub with 2,500+ community RL environments, hosted evaluations, sandboxed code execution, and dedicated/serverless model inference with native LoRA support. The company maintains open-source libraries (verifiers and prime-rl) used to build and train RL environments, and publishes frontier open research such as the INTELLECT and SYNTHETIC model/dataset series. Prime Intellect works with AI startups, enterprises, and 'neolab' customers such as Ramp and Zapier, helping them turn production traces and evaluations into custom-trained, post-trained agent models that outperform closed frontier models on specific workflows at lower cost and latency. The company has raised over $150M in total funding, including a $130M Series A led by Radical Ventures with participation from NVIDIA Ventures, Intel Capital, and Dell Technologies Capital, and reports over $100M in annualized revenue.
Skills
About the Role
You will embed with strategic customers to understand their agent architectures, failure modes, and goals. You will design RL environments, evaluation harnesses, verifiers, and agent scaffolding; configure training runs; and lead engagements through deployed, improved models. You will turn field insights into reusable reference implementations, templates, documentation, and technical content. You will also develop evaluation methods, prototype agent harnesses, experiment with reward design, and apply current agentic AI, evaluation, and post-training practices to customer work.
Requirements
- Hands-on experience building, evaluating, or deploying LLM-based agents
- Evaluation design expertise
- Understanding of RL and post-training concepts including GRPO, RLHF, reward modeling, and SFT
- Python skills
- Experience with Hugging Face, inference engines, or agent frameworks
- Customer-facing, consulting-adjacent technical, or technical founder experience
- Written and verbal communication skills
Responsibilities
- Embed with strategic customers to understand agent architectures, failure modes, and product goals
- Design and build custom RL environments, evaluation harnesses, and verifiers
- Architect agent scaffolding for customer workflows
- Configure and launch training runs, iterating on reward functions, rollout strategies, and evaluation criteria
- Lead technical engagements from discovery through deployed, improved models
- Codify repeatable customer patterns into reference implementations, templates, and documentation
- Shape the platform roadmap with customer feedback
- Build examples and recipes for customers and open-source contributors
- Contribute technical content including blog posts, tutorials, and case studies
- Develop evaluation methodologies for agentic behavior
- Prototype agent harnesses for real-world tasks
- Experiment with reward design, rubric construction, and environment shaping
- Stay current on agentic AI, evaluation, and post-training methods
Benefits
- Equity incentives
- Flexible work
- Visa sponsorship
- Relocation support
- Professional development budget
- Team off-sites
- Conference attendance