confidential
We are building a proprietary computational platform that transforms lead
optimization in drug discovery by replacing costly experimental screening with
automated physics-based prediction of molecular properties.
What we do
Pharma teams must evaluate 500 molecules after AI screening, but
experimental validation with synthesis and binding is slow and expensive.
Our proprietary platform predicts equilibrium constants governing binding and
other molecular processes.
Output: ranked list of candidates → 5–10 drug molecules for wet-lab testing
- Our goal is ~80% success in candidate selection
- ~1000× cost reduction
- Recently automated for small molecules and proteins
Why this is different
Existing free-energy methods (FEP / TI-based pipelines):
- Achieve ~30% success in realistic lead optimization
- Are computationally expensive and hard to scale
- Lack robustness across chemical space
Your role
- Develop physics-based and statistical models for molecular free-energy
prediction - Improve large-scale molecular ranking pipelines
- Validate predictions against experimental/simulated data
- Enhance automation, robustness, and numerical stability
- Work on drug discovery projects with design partners
Requirements
Must-have
- PhD/MSc in Computational Chemistry / Physics / Chemical Physics
- Strong background in molecular modeling or statistical mechanics
Nice-to-have
- Experience with free-energy methods (FEP, TI, MBAR, etc.)
- Protein–ligand simulation experience
- HPC / scalable simulation workflows
Why join
- Direct impact on real drug discovery pipelines
- Proprietary physics-based platform at scale
- Strong theory → algorithm → product loop
- High-leverage improvements across thousands of molecules
Terms
Compensation will initially be structured as equity (founding-stage role), with
transition to a full salary package upon successful fundraising.
To apply for this job email your details to tamar@scienceabroad.org.il
