Applied Research - RL & Agents
$150k - $300k • Remote • San Francisco • FullTime
Posted 3mo ago
About the job
Prime Intellect is building the open superintelligence stack, providing infrastructure for AI labs. Their platform, Lab, unifies compute, environments, evaluations, and training for frontier-scale post-training, including SFT, RL, tool use, and agent workflows. They are developing open-source models for long-horizon tasks and the platform their research team uses. This role is at the intersection of cutting-edge RL/post-training methods and applied agent systems, with a direct impact on how advanced models are aligned, deployed, and used. You will advance agent capabilities, build robust infrastructure, bridge applications and research, and prototype in the field.
Responsibilities
- Design and iterate on next-generation AI agents for workflow automation, reasoning-intensive tasks, and decision-making at scale.
- Develop systems and frameworks for reliable, efficient, and large-scale agent operation.
- Translate ambiguous objectives into clear technical requirements for product and research priorities.
- Rapidly design and deploy agents, evaluations, and harnesses for real-world tasks.
- Shape the direction and feature set for verifiers, the Environments Hub, and training services.
- Build high-quality examples, reference implementations, and 'recipes' to extend the stack.
- Prototype agents and eval harnesses tailored to real-world use cases and external systems.
- Pair with technical end-users to design environments, evaluations, and verifiers reflecting real workloads.
- Design and implement novel RL and post-training methods (RLHF, RLVR, GRPO) to align large models.
- Build evaluations and harnesses to measure reasoning, robustness, and agentic behavior.
- Prototype multi-agent and memory-augmented systems for downstream applications.
- Experiment with post-training recipes to optimize downstream performance.
- Rapidly prototype and iterate on AI agents for automation, workflow orchestration, and decision-making.
- Extend and integrate with agent frameworks to support evolving feature requests and performance requirements.
- Architect and maintain distributed training/inference pipelines for scalability and cost efficiency.
- Develop observability and monitoring (Prometheus, Grafana, tracing) for production deployments.
Requirements
- Strong background in machine learning engineering with experience in post-training, RL, or large-scale model alignment.
- Experience with agent frameworks and tooling (e.g., DSPy, LangGraph, MCP, Stagehand).
- Familiarity with distributed training/inference frameworks (e.g., vLLM, sglang, Accelerate, Ray, Torch).
- Track record of research contributions (publications, open-source contributions, benchmarks) in ML/RL.
- Passion for advancing state-of-the-art in reasoning and building practical, agentic AI systems.
- Strong technical writing abilities (documentation, blogs, papers) and research taste.
- Eagerness to drive collaborations with external partners and engage with the open-source community.
- Experience with web programming (React, TypeScript, Next.js) is a plus.
- Experience running LLM evaluations and/or synthetic data generation is a plus.
- Experience deploying containerized systems at scale (Docker, Kubernetes, Terraform) is a plus.
Benefits
- Cash Compensation Range of $150-300k
- Equity incentives
- Flexible Work (San Francisco or hybrid-remote)
- Visa Sponsorship & relocation support
- Professional Development budget
- Team Off-sites & conference attendance