ML Research Scientist, Environments & Harnesses

Your Impact at LILA

Lila is building a platform where AI and automation co-evolve to accelerate scientific discovery. Our AI Research team is looking to hire a ML Research Scientist to focus on synthetic RL environment pipelines and multi-agent harness design. These core pillars enable efficient scaling at training and test time to unlock scientific discovery. Lila’s scale and unique focus on experimental science means solving novel problems and building infrastructure that scales.

What You'll Be Building

• Design and prototype new harness capabilities — context compaction strategies, novel tool interfaces, long-horizon planning mechanisms, mult-agent swarms, and other innovations that expand what agents can do.
• Invent new types of RL environments — explore creative ways to turn scientific workflows, simulators, and real-world tasks into training signal.
• Build end-to-end pipelines for synthetic environment generation — transforming raw assets (papers, codebases, lab protocols) into validated, versioned training environments at scale.
• Prototype and validate environment designs — from initial concept through reward shaping, data collection, and integration with the training loop.
• Push the boundaries of multi-step reasoning — design and implement support for chained tasks, hierarchical goals, and complex evaluation scenarios.

What You'll Need to Succeed

• PhD (or equivalent experience) in Computer Science or a related quantitative field and two years of industry experience.
• A strong track record ideating on new harness designs or creating reinforcement learning environments at scale.
• Strong prototyping and coding skills — comfortable quickly building and iterating on new ideas in Python.
• Creativity and research intuition — ability to identify promising directions, design experiments, and navigate ambiguity.
• Familiarity with core concepts and algorithms in reinforcement learning.
• Solid software engineering fundamentals — clean code, version control, testing, and ability to integrate experimental work into shared infrastructure.

Bonus Points for

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