Machine Learning Scientist, Structure-Function ML, AI for Drug Discovery (AIDD)

About the role

A healthier future drives us to innovate, advancing science and ensuring access to healthcare for generations. Roche’s Research and Early Development organisations (gRED and pRED) leverage AI, data, and computational sciences to accelerate drug discovery. The Computational Sciences Center of Excellence (CoE) unifies efforts to harness data and AI, assisting scientists in delivering transformative medicines.

The Structure-Function ML group in Basel, part of Prescient Design (AI4DD) within the CoE, focuses on machine learning-based methods for de novo antibody design. We seek a Machine Learning Scientist with expertise in machine learning and protein structural biology to contribute to antibody design, develop new methods for protein therapeutics, and collaborate with global research teams.

Responsibilities

• Develop cutting-edge machine learning methods for modeling biological data, with a focus on structural biology.
• Deliver deep learning-based software solutions to accelerate drug discovery and therapeutic development, supporting de novo antibody design and lab-in-the-loop efforts.
• Collaborate with AI/ML scientists and global research teams, fostering close working relationships.
• Write structured, tested, and maintainable code, participating in proactive code reviews.
• Actively shape and contribute to a collaborative and innovative team culture.
• Partner with biologists and technologists to develop new methods for de novo protein design.

Requirements

• M.S. or PhD in Computer Science, Statistics, Physics, or a related technical field.
• 1+ years of hands-on experience designing and training machine learning models on large datasets.
• Published research on de novo antibody design in journals like Nature Biotechnology, NeurIPS, or ICML.
• Proficiency in Python and at least one deep learning framework (PyTorch, TensorFlow, or JAX).
• Experience with MLOps frameworks like Hydra and Weights & Biases.
• A public codebase of computational de novo antibody design (e.g., on GitHub).
• Demonstrated experience with modern techniques, including hallucination or folding models.
• Prior experience or familiarity with antibody sequence and structure data (a plus).
• Excellent communication skills in English and a passion for driving projects in cross-functional environments.

Pay

The expected salary range for this position, based on the primary location of New York, is $141,100–$262,100. Actual pay will be determined by experience, qualifications, geographic location, and other job-related factors. A discretionary annual bonus may be available based on individual and company performance.

Benefits

This position qualifies for the benefits detailed at Roche’s benefits page.