Applied Research - Forward-Deployed RL
$150k - $300k • Remote • San Francisco • FullTime
Posted 1d ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Research Engineer
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 post-training at scale, including SFT, RL, tool use, and agent workflows. They are focused on open-source models trained for long-horizon tasks and the platform used to build them. The company has raised significant funding from prominent investors and is seeking individuals to work at the intersection of frontier research, infrastructure, and go-to-market strategy for a nascent category.
Responsibilities
- Own applied RL programs from initial problem definition through deployed improvement loops.
- Understand customer workflows and business stakes to define measurable outcomes and learning objectives.
- Build environments and evaluations for post-training experiments.
- Run post-training experiments and deploy successful results.
- Determine which learnings can be generalized into Prime's shared stack.
- Work directly with external customer researchers, engineers, and leaders, ensuring accountability for research results and practical impact.
- Turn workflows and business goals into measurable environments, baselines, and evaluations.
- Improve domain agents using RL or other post-training methods, distinguishing model limitations from other failures.
- Carry successful experiments into deployment, measure their impact, and convert recurring components into reusable assets.
- Conduct technical and business discovery to create clear research plans, success measures, environments, and baselines.
- Execute RL, distillation, and other post-training experiments tied to deployment outcomes.
- Develop agent systems capable of tool use, memory, recovery, long horizons, and human oversight.
- Make deployment and adoption decisions, and contribute reusable artifacts to research, engineering, and product teams.
Requirements
- Experience in customer-embedded technical work, research engineering, technical founding, applied ML consulting with build ownership, or end-to-end post-training programs.
- Comfort interacting with senior external teams and connecting experimental evidence to business decisions.
- Hands-on experience building and debugging model-training, post-training, agent, evaluation, or related experimental loops.
- Strong experimental judgment, including establishing meaningful baselines, inspecting traces, attributing failures, and adapting approaches based on evidence.
- Proficiency in Python and the ability to build runnable, inspectable, and extensible artifacts for other researchers and engineers.
- Comfort owning ambiguous problems and keeping stakeholders informed.
- Demonstrated exceptional work through publications, open-source systems, benchmarks, or shipped products, including detailing challenges and approach changes.
Benefits
- Cash Compensation Range of $150-300k
- Equity incentives
- Flexible Work (San Francisco, New York, London, or remote)
- Visa Sponsorship & relocation support
- Professional Development budget
- Team Off-sites & conference attendance