Research Scientist - Computational Chemistry

We offer opportunities to do your life’s work while helping solve one of the most important technical and moral challenges of our time.

Full-time, in-office in Emeryville, California. Compensation includes equity.

Our mosquito work

Build the computational chemistry layer that connects molecular structure, physicochemical properties, formulation context, and observed mosquito behavior. Your work should help us choose more informative compounds to test, not merely explain results after the fact.

Key Responsibilities

Develop molecular representations and predictive models for compound effects on mosquito landing and related behavioral endpoints

Combine chemical structures and descriptors with formulation, dose, assay, environmental, and behavioral data

Design prospective evaluations that measure whether model-ranked compounds outperform conventional selection approaches

Quantify uncertainty, identify out-of-domain predictions, and propose experiments that distinguish competing chemical hypotheses

Partner with formulation chemists and machine-learning researchers to recommend the next compound, dose, formulation, or controlled variant to test

Build reproducible computational workflows with traceable structures, descriptors, model versions, and experimental outcomes

Qualifications

Ph.D. or equivalent research experience in computational chemistry, chemoinformatics, physical chemistry, medicinal chemistry, chemical engineering, or a related field

Experience with molecular descriptors, similarity methods, QSAR, molecular machine learning, or graph-based models

Strong Python skills and experience with tools such as RDKit or equivalent chemical-computing libraries

Ability to design leakage-resistant evaluations and interpret model performance in chemical rather than purely statistical terms

Clear scientific writing and close collaboration with experimental teams

Desired Attributes

Experience with active learning, Bayesian optimization, uncertainty calibration, or prospective molecular discovery

Knowledge of volatility, solubility, controlled release, odorants, or insect-active small molecules

Experience connecting computation to iterative wet-lab experiments

Interest in building open, reusable scientific methods rather than a one-time screening model

Our crop-protection work

Build the computational chemistry layer that connects molecular structure, physicochemical properties, formulation context, and observed insect behavior. Your work should help us choose more informative compounds to test, not merely explain results after the fact.

Key Responsibilities

Develop molecular representations and predictive models for compound effects on insect landing on crops and related behavioral endpoints

Combine chemical structures and descriptors with formulation, dose, assay, environmental, and behavioral data

Design prospective evaluations that measure whether model-ranked compounds outperform conventional selection approaches

Quantify uncertainty, identify out-of-domain predictions, and propose experiments that distinguish competing chemical hypotheses

Partner with formulation chemists and machine-learning researchers to recommend the next compound, dose, formulation, or controlled variant to test

Build reproducible computational workflows with traceable structures, descriptors, model versions, and experimental outcomes

Qualifications

Ph.D. or equivalent research experience in computational chemistry, chemoinformatics, physical chemistry, medicinal chemistry, chemical engineering, or a related field

Experience with molecular descriptors, similarity methods, QSAR, molecular machine learning, or graph-based models

Strong Python skills and experience with tools such as RDKit or equivalent chemical-computing libraries

Ability to design leakage-resistant evaluations and interpret model performance in chemical rather than purely statistical terms

Clear scientific writing and close collaboration with experimental teams

Desired Attributes

Experience with active learning, Bayesian optimization, uncertainty calibration, or prospective molecular discovery

Knowledge of volatility, solubility, controlled release, odorants, or insect-active small molecules

Experience connecting computation to iterative wet-lab experiments

Interest in building open, reusable scientific methods rather than a one-time screening model