ML Research Scientist, Environments & Harnesses

The role

The ML Research Scientist will focus on synthetic RL environment pipelines and multi-agent harness design. They will design new harness capabilities, invent RL environments, and build end-to-end pipelines for synthetic environment generation.

What you will do

• Design and prototype new harness capabilities
• Invent new types of RL environments
• Build end-to-end pipelines for synthetic environment generation
• Prototype and validate environment designs
• Push the boundaries of multi-step reasoning

Required qualifications

• PhD (or equivalent experience) in Computer Science or a related quantitative field
• Two years of industry experience
• Strong track record ideating on new harness designs or creating reinforcement learning environments at scale
• Strong prototyping and coding skills in Python
• Creativity and research intuition
• Familiarity with core concepts and algorithms in reinforcement learning
• Solid software engineering fundamentals

Nice to have

• Strong publication track record at conferences such as NeurIPS, ICML, and ICLR
• Background in biology, chemistry, or physics
• Experience building developer-facing libraries, APIs, or frameworks
• Familiarity with distributed compute (Ray, Modal) or LLM inference systems (vLLM, batching strategies)
• Experience with async Python, Pydantic, and workflow orchestration frameworks (Flyte, Airflow)

Benefits

• Medical, dental, and vision coverage
• Employer-paid life and disability insurance
• Flexible time off with generous company wide holidays
• Paid parental leave
• Educational assistance program
• Commuter benefits
• Company subsidized lunch program

About the company

Lila Sciences is building Scientific Superintelligence™ to solve humankind's greatest challenges. The company builds systems that can learn for themselves by combining advanced AI models with proprietary AI Science Factory™ instruments.