Senior / Principal ML Scientist, Foundation Models for Life Sciences

Lila Sciences Lila Sciences · AI Frontier · San Francisco, CA · AI

Research Scientist role focused on developing and training large-scale generative foundation models for life sciences applications, including biological sequence design and molecular structure prediction. The role involves end-to-end ML process from problem formulation to integration into a closed-loop discovery engine, with a strong emphasis on research and publications.

What you'd actually do

  1. Drive research on foundation models for life science applications, including but not limited to biological sequence design, structure prediction, and multimodal scientific reasoning
  2. Design, train, and evaluate large-scale generative models on biological and chemical data, integrating domain-specific constraints and priors
  3. Contribute to the end-to-end ML process within Lila's "Lab-in-the-Loop" lifecycle: steer data generation strategy, build pipeline models, and design feedback loops where experimental results improve model performance
  4. Translate complex biological questions into well-defined ML problems and interpret model outputs in collaboration with wet-lab scientists and computational biologists
  5. Advance research standards and methodology within the foundation models program, contributing insights that influence approaches across adjacent teams

Skills

Required

  • PhD in Computer Science, Machine Learning, Computational Biology, or a related quantitative field
  • Multiple high-impact first-author or senior-author publications at premier venues (NeurIPS, ICML, ICLR, Nature Methods, Nature Biotechnology, or equivalent)
  • Deep expertise in large-scale generative model architectures and training
  • hands-on experience training models on distributed infrastructure
  • Demonstrated ability to formulate and drive research programs independently, from problem definition through publication and deployment
  • Fluency across ML and at least one life science domain (molecular biology, genomics, protein engineering, nucleic acid design, or related)
  • experience designing computational experiments grounded in biological reality
  • Strong track record of cross-functional collaboration with experimental scientists, translating between ML and biology
  • Expertise in ML frameworks (PyTorch, JAX, or TensorFlow)
  • experience with large-scale distributed training infrastructure (AWS, GCP, or on-prem clusters)

Nice to have

  • Experience in computational protein design, particularly antibody and nanobody engineering
  • Experience designing biological sequences or molecular structures with demonstrated wet-lab validation
  • Contributions to open-source ML tools, frameworks, or benchmark datasets for scientific applications
  • Experience with agentic frameworks or active learning loops in scientific contexts
  • High-impact publications or open‑source contributions in AI for Science in relevant venues (NeurIPS, ICML, ICLR, AAAI, Nature Methods, Nature Biotechnology, or equivalent)

What the JD emphasized

  • high-impact first-author or senior-author publications at premier venues
  • Deep expertise in large-scale generative model architectures and training
  • hands-on experience training models on distributed infrastructure
  • demonstrated ability to formulate and drive research programs independently
  • Strong track record of cross-functional collaboration with experimental scientists

Other signals

  • foundation models
  • generative models
  • large-scale training
  • life sciences
  • scientific discovery