Back to jobs

Applied Research - RL & Agents

Prime Intellect
San FranciscoFull-time
AI tools:DSPyLangGraphMCPStagehandvLLMsglangAccelerate

Upload your resume once and Scout applies for you

Apply with Scout
Share this job:LinkedInXSave image

This applied research role develops reinforcement-learning methods, evaluations, and agents for practical workflows. The engineer will work across research and infrastructure, prototyping agent systems and helping shape platform features such as verifiers and training services.

  • Permanent
  • Hybrid

Skills and expertise

RLHFRLVRGRPODSPyLangGraphMCPvLLMRay

Key responsibilities

  • Design and implement RL and post-training methods to align models with domain-specific tasks.
  • Build evaluations, harnesses, and agent prototypes for real-world workflows and external systems.
  • Develop distributed training and inference pipelines and monitor their production reliability.

How this job compares

Compared with 329 open mid-level machine learning jobs on November 21, 2026.

Pay
This job does not publish its pay. The 119 open mid-level machine learning jobs that publish US pay start at $180K a year on average.
Similar open jobs
We Love AI Jobs lists 329 open mid-level machine learning jobs at 145 companies.
Remote work
This job is hybrid. 66 of the 329 mid-level machine learning jobs (20%) are remote.
AI in this role
High. AI is the core of the work: building, training or deploying AI systems. The role directly researches and implements reinforcement learning, post-training, model evaluations, and agent systems. These are central day-to-day responsibilities.

Full 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

This is a role at the intersection of cutting-edge RL/post-training methods and applied agent systems. You’ll have a direct impact on shaping how advanced models are aligned, deployed, and used in the real world by:

• Advancing Agent Capabilities: Designing and iterating on next-generation AI agents that tackle real workloads—workflow automation, reasoning-intensive tasks, and decision-making at scale.

• Building Robust Infrastructure: Developing the systems and frameworks that enable these agents to operate reliably, efficiently, and at massive scale.

• Bridge Between Applications & Research: Translate ambiguous objectives into clear technical requirements that guide product and research priorities.

• Prototype in the Field: Rapidly design and deploy agents, evals, and harnesses for real-world tasks to validate solutions.

Application-Driven Research & Infrastructure

• Shape the direction and feature set for verifiers, the Environments Hub, training services, and other research platform offerings.

• Build high‑quality examples, reference implementations, and “recipes” that make it easy for others to extend the stack.

• Prototype agents and eval harnesses tailored to real-world use cases and external systems.

• Pair with technical end‑users (research teams, infra‑heavy customers, open‑source contributors) to design environments, evals, and verifiers that reflect real workloads.

Post-training & Reinforcement Learning

• Design and implement novel RL and post-training methods (RLHF, RLVR, GRPO, etc.) to align large models with domain-specific tasks.

• Build evaluations and harnesses and to measure reasoning, robustness, and agentic behavior in real-world workflows.

• Prototype multi-agent and memory-augmented systems to expand capabilities for downstream applications.

• Experiment with post-training recipes to optimize downstream performance.

Agent Development & Infrastructure

• 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, ensuring scalability and cost efficiency.

• Develop observability and monitoring (Prometheus, Grafana, tracing) to ensure reliability and performance in 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 the 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 broader open-source community.

Nice-to-Haves

• Experience with web programming (React, TypeScript, Next.js).

• Experience running LLM evaluations and/or synthetic data generation.

• Experience deploying containerized systems at scale (Docker, Kubernetes, Terraform).

What We Offer

• 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

Growth Opportunity

You’ll join a mission-driven team working at the frontier of open, superintelligence infra. In this role, you’ll have the opportunity to:

• Shape the evolution of agent-driven solutions—from research breakthroughs to production systems used by real customers.

• Collaborate with leading researchers, engineers, and partners pushing the boundaries of RL and post-training.

• Grow with a fast-moving organization where your contributions directly influence both the technical direction and the broader AI ecosystem.

If you’re excited to move fast, build boldly, and help define how agentic AI is developed and deployed, we’d love to hear from you.

Ready to build the open superintelligence infrastructure of tomorrow?

Apply now to help us make powerful, open AGI accessible to everyone.

Upload your resume once and Scout applies for you

Apply with Scout

Similar jobs