Your Impact at LILA

Lila is building a platform where AI and automation co-evolve to solve the hardest problems in medicine. Within Life Sciences AI, the AI for Protein Engineering team builds models and systems that take a biologic from design specification to wet-lab validated lead.

We're hiring a machine learning scientist to design molecules on real programs and turn what they learn into capabilities that generalize across programs. The ideal candidate is an exceptional builder with strong biological intuition: someone who can turn work on individual campaigns into reliable, extensible systems that improve how we design molecules across programs. You'll work closely with domain scientists, platform teams, and AI researchers to connect specialist protein design models to Lila's broader autonomous science platform.

What You'll Be Building

• Design molecules for active biologics programs, partnering with domain scientists to translate target, mechanism, and experimental constraints into actionable design hypotheses.
• Develop reasoning capabilities for drug discovery, including orchestrating design workflows.
• Design and maintain benchmarks and evaluation infrastructure that measure whether design workflows produce useful, generalizable decisions across biologics programs.
• Own operations around reproducibility, throughput, and inference cost of computational design workflows.
• Work with domain scientists to understand how designs are prioritized and turn that judgment into ML objectives and evaluation criteria.

What You'll Need to Succeed

• MS or PhD in computer science, machine learning, computational biology, biophysics, bioengineering, or a similar quantitative field.
• Strong software engineering and system design fundamentals.
• Rigor in evaluation and dataset design: how benchmarks leak, why a good validation number fails downstream, and how to measure whether an automated system is making good decisions.
• Strong cross-functional communication skills.
• Domain expertise in protein sequence, structure, and function.

Bonus Points For

• Experience building reasoning models, agents, planning systems, or multi-step ML orchestration.
• Exposure to designing antibodies, nanobodies, enzymes, peptides, or other therapeutic proteins within design-test-learn loops.
• Experience in developing evaluation harnesses, model registries, or benchmark suites.
• Training or serving models at scale: distributed training, GPU efficiency, high-throughput inference.
• Publications, open-source contributions, or applied research outputs in AI for Science venues.