Tailored Management
Job Title: Machine Learning Engineer
Location: 1 DNA Way, South San Francisco, CA 94080
Duration: 1-Year Contract (with possibility for extension or conversion)
Pay Rate: $36.65 - $81.65 per hour (W2)
Overview Join Genentech's Prescient Design, a cutting-edge team within Research and Early Development (gRED), focused on developing structural and machine learning-based molecular design methods. This role leads projects applying novel machine learning techniques for molecular optimization, targeting both small and large molecule drug design. Key focus areas include probabilistic molecular property prediction pipelines and Bayesian acquisition for active learning-driven drug discovery, with potential involvement in molecular generative modeling.
Key Responsibilities
Collaborate within Prescient Design and with gRED computational scientists, chemists, and biologists. Develop machine learning and Bayesian optimization workflows for analyzing and designing small and large molecules. Build close partnerships across small molecule and protein therapeutic development teams. Manage current projects and innovate new ideas, engineering pipelines for probabilistic property prediction, Bayesian acquisition, and generative modeling.
Required Qualifications
PhD in quantitative fields such as Computer Science, Chemistry, Chemical Engineering, Computational Biology, or Physics; or MS with 3+ years of industry experience. Hands-on experience with production-ready machine learning libraries (e.g., PyTorch, Lightning, Weights & Biases). Proven track record with at least one high-impact first-author publication or equivalent achievement. Excellent written, visual, and verbal communication and collaboration skills.
Desired Qualifications
Experience with molecular dynamics, physical modeling, and cheminformatics toolkits like rdkit. Expertise in molecular property prediction, computational chemistry, de novo drug design, medicinal chemistry, small molecule design, self-supervised learning, geometric deep learning, Bayesian optimization, probabilistic modeling, and statistical methods. Public computational project portfolio (e.g., GitHub).
Overview Join Genentech's Prescient Design, a cutting-edge team within Research and Early Development (gRED), focused on developing structural and machine learning-based molecular design methods. This role leads projects applying novel machine learning techniques for molecular optimization, targeting both small and large molecule drug design. Key focus areas include probabilistic molecular property prediction pipelines and Bayesian acquisition for active learning-driven drug discovery, with potential involvement in molecular generative modeling.
Key Responsibilities
Collaborate within Prescient Design and with gRED computational scientists, chemists, and biologists. Develop machine learning and Bayesian optimization workflows for analyzing and designing small and large molecules. Build close partnerships across small molecule and protein therapeutic development teams. Manage current projects and innovate new ideas, engineering pipelines for probabilistic property prediction, Bayesian acquisition, and generative modeling.
Required Qualifications
PhD in quantitative fields such as Computer Science, Chemistry, Chemical Engineering, Computational Biology, or Physics; or MS with 3+ years of industry experience. Hands-on experience with production-ready machine learning libraries (e.g., PyTorch, Lightning, Weights & Biases). Proven track record with at least one high-impact first-author publication or equivalent achievement. Excellent written, visual, and verbal communication and collaboration skills.
Desired Qualifications
Experience with molecular dynamics, physical modeling, and cheminformatics toolkits like rdkit. Expertise in molecular property prediction, computational chemistry, de novo drug design, medicinal chemistry, small molecule design, self-supervised learning, geometric deep learning, Bayesian optimization, probabilistic modeling, and statistical methods. Public computational project portfolio (e.g., GitHub).