Senior/Principal Machine Learning Scientist - Structure and Simulation

2w2 weeks ago

Genentech

New York City, US · Full-time · $141,300 – $172,400

About this role

A healthier future drives Roche to innovate and advance science for accessible healthcare. Advances in AI, data, and computational sciences transform drug discovery at Genentech's gRED and pRED. The Computational Sciences Center of Excellence harnesses AI to deliver innovative medicines worldwide.

At Roche's AI for Drug Discovery group (Prescient Design), develop models for a unified drug discovery process across modalities, structures, and simulations. Build high-quality research at the machine learning and biology intersection with direct therapeutic impact. Transform balkanized processes into coherent lab-in-the-loop systems.

Join a strategic group enabling seamless data sharing and model access across gRED and pRED. Collaborate with scientists leveraging novel computational models to accelerate R&D. Contribute to consolidating machine learning projects into single coherent frameworks.

Perform exceptional research as a Senior or Principal Scientist in large molecule drug discovery. Lead or contribute to initiatives integrating heterogeneous biological and chemical data. Drive step-changes in machine learning for structure-based hit finding and lead optimization.

Requirements

Significant education in computer science or the life and physical sciences, or equivalent work experience
Experience designing and building machine learning systems, particularly for molecules and biological sequences
Demonstrated experience with Python and deep learning libraries such as PyTorch, TensorFlow, or JAX
Familiarity with areas of modern machine learning research, such as reinforcement learning, sampling, and multimodal representation learning
Demonstrated research experience, including at least one first author publication or equivalent
Strong communication and collaboration skills
Portfolio of computational projects (available on e.g. GitHub)

Responsibilities

Develop novel machine learning methods to answer challenging research questions in large molecule drug discovery
Work with biological and chemical data from heterogeneous sources
Contribute to (Senior) or lead (Principal) an initiative to consolidate projects in machine learning theory into a single coherent model for lab-in-the-loop drug discovery
Design and build machine learning systems for molecules and biological sequences
Leverage data and novel computational models to accelerate R&D
Integrate simulation methods with black-box models for affinity and high-concentration properties
Transform drug discovery from balkanized processes into unified approaches across modalities