Computational Biophysics Scientist at lilasciences

Compensation

$140,800 – $217,800/yr

Setup: Hybrid
Location: San Francisco, California
Type: Full-time
Level: not_specified
Posted: Aug 3, 2026

Description

Lila Sciences is looking for a Computational Biophysics Scientist to develop and implement biophysics tools for AI-driven drug discovery. This role involves defining experiment setups, validating molecular simulation workflows using MM/GBSA and free-energy perturbation methods, and ensuring scientific rigor for automated workflows. The scientist will collaborate with various teams to create scalable platforms for drug discovery.

Required Skills

Computational Biophysics
Molecular Simulation
Statistical Mechanics
Binding Free-Energy Methods
MM/GBSA
Free-Energy Perturbation Methods
OpenMM
OpenFE

Additional Information

Minimum Education: PhD or equivalent experience in computational biophysics, computational chemistry, chemical physics, biophysics, physics, chemistry, or a related field.
Required Previous Experiences: Deep hands-on experience with molecular dynamics simulation, MM/GBSA, and free-energy perturbation methods for RBFE and ABFE.
Practical experience with open-source molecular simulation and free-energy packages, with strong preference for OpenMM and OpenFE.
Strong understanding of how to parameterize molecular systems and validate that simulation setups are scientifically sound.
Demonstrated history of modeling protein-ligand binding and interpreting results for scientific decision-making.
Ability to reason from biophysical first principles while also building practical workflows that other teams can use.
Experience translating complex scientific methods into tooling requirements, review standards, and operational workflows.
Preferred Qualifications: Industry drug discovery experience, especially in structure-based or computational discovery programs.
Familiarity with large-scale GPU simulation infrastructure or distributed scientific computing.
Experience building automated or semi-automated scientific workflows.
Familiarity with cofolding, structure prediction, or ML-assisted molecular modeling methods.
Experience defining benchmark suites, regression tests, or validation harnesses for scientific software.
Experience designing perturbation maps for robust RBFE statistics.
Experience integrating machine-learned interatomic potentials or hybrid force-field simulations.
Experience with active learning or fine-tuning of simulation parameters against experimental data for defined chemical or biological systems.
Comfort working with LLM agents or agentic workflow systems.