Research Engineer (Reinforcement Learning)

Epsilab

San Francisco (CA)

In loco

USD 125.000 - 220.000

Tempo pieno

8 giorni fa

Una candidatura completa in un minuto

Curriculum e lettera di presentazione personalizzati, pronti da inviare.

Supera i filtri ATS

Descrizione del lavoro

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

Competenze

  • 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.

Mansioni

  • 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.

Conoscenze

Python programming
Machine learning
Reinforcement learning
Experiment design
Communication

Strumenti

Linux
Docker
APIs

Descrizione del lavoro

About Epsilab

Epsilab is a YC F26 startup building the training grounds for real-world AI agents. We create high-fidelity reinforcement learning environments that recreate enterprise software, tools, and complex professional workflows, helping agents learn to complete long-horizon tasks.

We’re a fast-growing startup working with frontier AI labs. Our team is extremely flat, fast-moving, and creative: you’ll work directly with the founders, contribute ideas across the company, and take ownership from first experiment to shipped product. We value technical curiosity, clear thinking, and people who turn ambitious ideas into working systems.

About the role

We’re hiring a Research Engineer focused on reinforcement learning to build environments, evaluation systems, and experimental infrastructure for training capable AI agents. You’ll investigate what makes agents succeed or fail on complex workflows, then turn those findings into better tasks, reward signals, and reliable research tools.

You’ll work at the intersection of research and engineering, moving quickly from a hypothesis to a reproducible experiment and a system that frontier lab partners can use.

What you’ll do
  • Build stateful RL environments with realistic tools, application behavior, reproducible resets, and verifiable outcomes.
  • Develop reward functions, graders, and evaluation harnesses that measure task completion and catch shortcuts, reward hacking, and brittle behavior.
  • Design and run experiments on agent performance, task difficulty, generalization, and long-horizon reliability.
  • Analyze agent trajectories and environment state to distinguish model failures from task, tooling, or grading issues.
  • Build pipelines for generating, validating, and replaying tasks and trajectories, with quality checks that combine programmatic validation and expert judgment.
  • Collaborate with domain experts and frontier lab researchers to translate real-world workflows and research questions into useful training environments.
What you’ll bring
  • 3+ years of relevant experience in research engineering, machine learning, or software engineering.
  • Strong Python skills and experience building and debugging systems using Linux, Docker, and APIs.
  • A practical understanding of reinforcement learning, including rewards, policies, exploration, and evaluation.
  • Experience implementing ML experiments or agent systems, with careful measurement and reproducible results.
  • Sound experimental judgment: you can choose useful baselines, interpret noisy results, and identify misleading metrics.
  • The initiative to tackle open-ended problems, communicate findings clearly, and ship in a fast-moving startup.
Helpful experience
  • LLM post-training, RL algorithms, PyTorch or JAX, agent benchmarks, reward modeling, or automated environment validation.
  • Research publications and open-source contributions are welcome; a PhD is not required.
Location and compensation
  • Full-time, in person in San Francisco, California. You must be based in the US and able to work from our San Francisco office by your start date.
  • US visa sponsorship available.
  • Annual base salary: $125,000–$220,000, based on relevant experience and skills.
Ottieni la revisione del curriculum gratis e riservata.

o trascina qui il file.

Similar jobs

Offerte di lavoro simili che vale la pena confrontare

Senior Research Engineer
Senior Research Engineer

turing • Stati Uniti

Remoto
USD 250.000 - 350.000
Equity
High autonomy
RL Environment Software Engineer – AfterQuery
RL Environment Software Engineer – AfterQuery

talentpluto • San Francisco (CA)

In loco
USD 180.000 - 220.000
RL Research Engineer: Real-World Environments & Experiments
RL Research Engineer: Real-World Environments & Experiments

Epsilab • San Francisco (CA)

In loco
USD 125.000 - 220.000
Staff Research Engineer
Staff Research Engineer

turing • Stati Uniti

Remoto
USD 250.000 - 400.000
Equity
Conference publication opportunities
High autonomy
Software Engineer, RL Environments
Software Engineer, RL Environments

True Talent Solutions Partners • San Francisco (CA)

In loco
USD 260.000 - 290.000
Research Engineer Intern - Environments, Data and Post-Training
Research Engineer Intern - Environments, Data and Post-Training

Thinklance LLP • San Francisco (CA)

In loco
USD 100.000 - 145.000
Meals stipend
Equinox gym membership
Laundry reimbursement
+1
Staff Research Engineer, Enterprise Knowledge
Staff Research Engineer, Enterprise Knowledge

turing • Stati Uniti

Remoto
USD 250.000 - 400.000
Remote | Member of Technical Staff, Research Engineering — $400,000–$800,000/year
Remote | Member of Technical Staff, Research Engineering — $400,000–$800,000/year

24-Mag Llc • New York (NY)

Remoto
USD 400.000 - 800.000
Fully remote
Research Scientist - RL Training
Research Scientist - RL Training

snorkelai • Stati Uniti

Remoto
USD 200.000 - 350.000
RL AI Research Scientist
RL AI Research Scientist

Pokee AI • Stati Uniti

Remoto
USD 150.000 - 230.000