Senior / Principal Scientist, AI for Protein Engineering

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

Senior/Principal Scientist role focused on AI for protein engineering, specifically antibody design and engineering. The role involves developing and executing design workflows, translating biological requirements into ML problems, adapting state-of-the-art AI methods, and collaborating with experimental scientists for validation and active learning loops. The position requires a PhD and strong expertise in both ML and protein biology, with a focus on delivering wet-lab validated biomolecules.

What you'd actually do

  1. Develop and own protein design and engineering workflows for antibody campaigns, including de novo design, affinity maturation, and developability optimization
  2. Execute design workflows end-to-end for active campaigns and deliver wet-lab-validated leads against program milestones
  3. Translate campaign requirements — epitope selection, affinity targets, biophysical constraints, and developability criteria — into well-defined ML problems and design specifications
  4. Adapt and extend state-of-the-art AI methods (generative models, protein language models, structure-conditioned design) to the specific demands of antibody and broader biomolecule engineering
  5. Partner with the Life Science Research team on design validation, building active learning loops where wet-lab data refines and improves model performance

Skills

Required

  • PhD in Computational Biology, Computer Science, Machine Learning, Biophysics, or a related quantitative field
  • Proven track record of successful design of wet-lab-validated biomolecules through AI
  • Deep ML expertise with the ability to modify and adapt state-of-the-art AI approaches for protein engineering
  • Strong fluency across both ML and protein biology, with hands-on understanding of antibody design
  • Demonstrated ability to drive a research and engineering program independently
  • Track record of close collaboration with experimental scientists and clear communication across the ML/biology boundary

Nice to have

  • Direct experience designing antibodies, nanobodies, or other therapeutic proteins for clinical or therapeutic pipelines
  • Experience with structure prediction, generative protein design (diffusion, flow-matching, or similar), and protein language models in a production research setting
  • Experience in structural biology and conformational dynamics
  • Experience extending design methods to additional modalities such as enzymes, peptides, or other engineered biomolecules
  • High-impact publications or open-source contributions in AI for Science (NeurIPS, ICML, ICLR, Nature Methods, Nature Biotechnology, or equivalent)
  • Experience designing or operating active learning loops between computational design and high-throughput experimental validation

What the JD emphasized

  • Proven track record of successful design of wet-lab-validated biomolecules through AI
  • Deep ML expertise with the ability to modify and adapt state-of-the-art AI approaches for protein engineering, not just apply them off-the-shelf
  • Strong fluency across both ML and protein biology, with hands-on understanding of antibody design
  • Demonstrated ability to drive a research and engineering program independently, from problem definition through experimental validation and iteration
  • Track record of close collaboration with experimental scientists and clear communication across the ML/biology boundary

Other signals

  • develop and execute methods and workflows for antibody campaigns
  • translate campaign requirements into ML problems
  • adapt and extend state-of-the-art AI methods for protein engineering
  • partner with Life Science Research team on design validation
  • build active learning loops