Senior Machine Learning Scientist, (BRAID - Perturbation Biology)

$165,200 - $306,800/Yr

Genentech - San Francisco, CA

Full-time - Senior

San Francisco, CA

Chemical Manufacturing

About the position

Genentech is seeking a highly skilled and motivated Senior Machine Learning Scientist to join the Perturbation Biology group within the BRAID department. This role focuses on developing advanced Machine Learning models to derive actionable insights from large-scale high-content perturbation experiments, aiming to enhance experimental design and predict outcomes for drug and target identification. The position emphasizes innovation through cutting-edge ML methods with real-world applications in target and drug discovery.

Responsibilities

• Design and apply Machine Learning algorithms to improve experimental design of high-content perturbation screens.
• Integrate various data modalities such as molecular structures, omics data, images, and text.
• Collaborate with interdisciplinary teams including biologists, chemists, and data scientists.
• Build and scale Machine Learning techniques for massive datasets and deploy novel algorithms.
• Publish research in top-tier ML venues and present results at scientific conferences and workshops.

Requirements

• PhD degree in a quantitative field (e.g., Computer Science, Statistics, Mathematics) or in the physical/life sciences (e.g., Chemistry, Biology) with a strong quantitative focus.
• Proven track record of developing and applying advanced ML models in research or industry settings.
• Demonstrated interest in biology and chemistry related to treatment discovery and development.
• Proficiency in scientific programming in Python.
• Extensive experience with Machine Learning frameworks (e.g., PyTorch, JAX, Tensorflow).
• Strong background in statistics, probabilistic modeling, and data analysis.
• Excellent communication, collaboration, and problem-solving skills.
• Strong publication record in relevant conferences.

Nice-to-haves

• Practical experience in predictive modeling of perturbation datasets with high-content readout.
• Modeling perturbation effects on heterogeneous cell states in transcriptomics data.
• Predictive and/or generative modeling on molecules and chemistry applications.
• Experience in multimodal data integration, particularly with clinical patient data.

Benefits

• Relocation benefits available.
• Discretionary annual bonus based on individual and company performance.