RL Environment Engineer - World-Scale Agent Training (Remote)

Bespoke Labs; United States; On-site; USD 27,552 - 82,656; Part time

Job summary

Bespoke Labs is seeking an experienced ML Engineer to work with our research team on creating reinforcement learning environments. This role involves designing observation spaces, action spaces, and reward signals for agent training.

The ideal candidate will have 3+ years of experience in ML engineering, strong proficiency in Python and deep learning, and experience with LLMs. The position offers flexible remote work and competitive hourly compensation.

Qualifications

• 3+ years of ML engineering experience in research or production.
• Strong Python and deep learning proficiency with PyTorch.
• Hands-on experience with LLM post-training techniques.

Responsibilities

• Design observation spaces, action spaces, reward signals, and success criteria for new RL environments.
• Build infrastructure for world-scale RL training.
• Work directly with research teams on RL environment and task creation.

Skills

ML engineering experience

Python proficiency

Deep learning (PyTorch preferred)

Experience with LLM post-training

Familiarity with RL frameworks

Experience with cloud or HPC

Understanding of evaluation methodology

Job description

Bespoke Labs is seeking an experienced ML Engineer to work with our research team on creating reinforcement learning environments. This role involves designing observation spaces, action spaces, and reward signals for agent training.

The ideal candidate will have 3+ years of experience in ML engineering, strong proficiency in Python and deep learning, and experience with LLMs. The position offers flexible remote work and competitive hourly compensation.