RL Research Engineer: Real-World Environments & Experiments

Epsilab

San Francisco (CA)

On-site

USD 125,000 - 220,000

Full time

8 days ago

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Epsilab is seeking a Research Engineer focused on reinforcement learning to build environments, evaluation systems, and experimental infrastructure for training capable AI agents. You’ll work at the intersection of research and engineering, turning hypotheses into reproducible experiments and a system that frontier lab partners can use.

You’ll collaborate with domain experts to translate real-world workflows and research questions into useful training environments, and you’ll design stateful

Qualifications

  • 3+ years in research engineering, ML, or software engineering.
  • Strong Python skills; Linux, Docker, and API usage.
  • Solid understanding of reinforcement learning, rewards and evaluation.
  • Experience building ML experiments or agent systems with reproducible results.
  • Ability to tackle open-ended problems and ship quickly in a startup.

Responsibilities

  • Build stateful RL environments with realistic tools and verifiable outcomes.
  • Develop reward functions, graders, and evaluation harnesses.
  • Design experiments on agent performance and long-horizon reliability.
  • Analyze agent trajectories to distinguish model failures.
  • Build pipelines for generating and validating tasks and trajectories.
  • Collaborate with domain experts to translate workflows into training environments.

Skills

Python programming
Machine learning
Reinforcement learning
Experiment design
Communication

Tools

Linux
Docker
APIs

Job description

Epsilab is seeking a Research Engineer focused on reinforcement learning to build environments, evaluation systems, and experimental infrastructure for training capable AI agents. You’ll work at the intersection of research and engineering, turning hypotheses into reproducible experiments and a system that frontier lab partners can use.

You’ll collaborate with domain experts to translate real-world workflows and research questions into useful training environments, and you’ll design stateful

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

RL Research Engineer: Build Environments & Experiments
RL Research Engineer: Build Environments & Experiments

Mecka • New York (NY)

On-site
USD 170,000 - 300,000
Research Engineer (Reinforcement Learning)
Research Engineer (Reinforcement Learning)

Epsilab • San Francisco (CA)

On-site
USD 125,000 - 220,000
RL Environment Engineer for Real Enterprise Data
RL Environment Engineer for Real Enterprise Data

Sunset • New York (NY)

On-site
USD 220,000 - 320,000
Meaningful equity
Medical, dental & vision
Unlimited PTO
+3
RL Environments Engineer for AI Agents
RL Environments Engineer for AI Agents

Impax Recruitment • San Francisco (CA)

On-site
USD 270,000 - 330,000
2% equity
Profit sharing
Senior RL Environments Engineer for Real-World Science
Senior RL Environments Engineer for Real-World Science

Lumos • San Francisco (CA)

On-site
USD 160,000 - 220,000
RL Environment Engineer - World-Scale Agent Training (Remote)
RL Environment Engineer - World-Scale Agent Training (Remote)

Bespoke Labs • United States

Remote
USD 27,552 - 82,656
Senior RL Environment Engineer — Real-World Data Systems
Senior RL Environment Engineer — Real-World Data Systems

Replay • New York (NY)

On-site
USD 220,000 - 320,000
Base salary $220–320K
Equity
Medical, dental, and vision insurance
+4
RL Environment Engineer: Build & Benchmark Learning Agents
RL Environment Engineer: Build & Benchmark Learning Agents

mecka • San Francisco (CA)

On-site
USD 140,000 - 210,000
Research Engineer, RL Env
Research Engineer, RL Env

Kindredventures • San Francisco (CA)

On-site
USD 140,000 - 220,000
Research Engineer, RL Env
Research Engineer, RL Env

mecka • San Francisco (CA)

On-site
USD 140,000 - 210,000