Job Title: Machine Learning Engineer
Location: 1 DNA Way, South San Francisco, CA 94080
Duration: 12-month contract (possibility of extension)
Work Model: Hybrid
About the Role
Client’s Prescient Design team within the Research and Early Development (gRED) organization is seeking a Machine Learning Engineer to help advance structural and machine learning-based approaches for molecular design.
You will play a key role in developing and deploying advanced ML techniques for molecular optimization, property prediction, and active learning-driven drug discovery. This is an exciting opportunity to contribute to cutting-edge science while collaborating with top-tier researchers in computational biology, chemistry, and drug development.
Key Responsibilities
- Develop and deploy machine learning and Bayesian optimization workflows for molecular property prediction and optimization.
- Collaborate with scientists across Prescient Design and gRED to design, analyze, and optimize small and large molecule therapeutics.
- Engineer production-ready pipelines for probabilistic modeling, active learning, and molecular generative modeling.
- Support drug discovery initiatives by applying ML models to enable target-driven design campaigns.
- Contribute to existing research projects and help define new opportunities for machine learning in molecular science.
Qualifications
- PhD in Computer Science, Chemistry, Chemical Engineering, Computational Biology, Physics, or a related quantitative field
- – or – MS degree with 3+ years of relevant industry experience.
- Strong experience in software engineering and production-grade ML workflows using libraries such as PyTorch, Lightning, and Weights & Biases.
- Proven research track record (e.g., at least one high-impact first-author publication or equivalent).
- Excellent written, visual, and verbal communication skills with a collaborative mindset.
Must Have Skills & Experience
Candidates with strong expertise in one or more of the following areas are highly encouraged to apply (listed in order of importance):
- Molecular property prediction
- Probabilistic modeling and inference
- Bayesian optimization or active learning
- Production software engineering or pipeline optimization
- Cheminformatics
Additional desirable skills include:
- Experience with physical modeling methods (e.g., molecular dynamics).
- Familiarity with cheminformatics toolkits (e.g., RDKit).
Background in:
- De novo drug design
- Computational or medicinal chemistry
- Small molecule design
- Self-supervised or geometric deep learning
- Statistical modeling and data analysis
- Public portfolio (e.g., GitHub) demonstrating computational or ML projects.
