Principal Scientist, Portfolio & gRED Interface-Biologics, AI for Drug Discovery (AIDD)
About The Position
Advances in AI, data, and computational sciences are transforming drug discovery and development. Roche’s Research and Early Development organisations at Genentech (gRED) and Pharma (pRED) have demonstrated how these technologies accelerate R&D, leveraging data and novel computational models to drive impact. Seamless data sharing and access to models across gRED and pRED are essential to maximising these opportunities. The new Computational Sciences Center of Excellence (CoE) is a strategic, unified group whose goal is to harness the transformative power of data and Artificial Intelligence (AI) to assist our scientists in both pRED and gRED to deliver more innovative and transformative medicines for patients worldwide. At Roche's AI for Drug Discovery (AIDD) group within the Computational Sciences Center of Excellence, we are driving a paradigm shift in how large molecule drug discovery is conducted. Our vision is to integrate artificial intelligence and machine learning into every stage of antibody discovery—from target assessment and design optimization to developability prediction and portfolio prioritization. But vision without execution is just strategy. We need exceptional scientist-leaders who can take our computational methods and translate them into measurable impact on active portfolio projects. We need people who understand both the science deeply and the politics, constraints, and needs of our discovery organizations. We need leaders who can build and develop teams that deliver. You would be stepping into a role with outsized impact: driving portfolio applications of advanced ML models directly to gRED projects, serving as a trusted technical advisor to gRED leadership, and building a team of computational scientists who collectively raise the bar for what's possible in large molecule design. Large molecule drug discovery is at an inflection point. The right computational approaches applied at the right time can de-risk projects, identify better leads, and accelerate timelines. But this only happens when computational scientists are deeply integrated into portfolio teams and leadership trusts their insights. This role is about being that trusted voice—the person who brings rigor, innovation, and clarity to one of Roche's most important discovery areas.
Requirements
- PhD in Computational Biology, Biophysics, Immunology, Chemistry, or Computer Science with significant experience in drug discovery (10+ years total, 5+ in ML/computational methods for biologics)
- Expertise in computational methods for large molecule design, with particular depth in developability assessment, biophysical modeling, or antibody engineering
- Track record of developing novel computational methods that have influenced real drug discovery projects
- First-author publications demonstrating research innovation in computational drug discovery or related fields
- Understanding of the full lifecycle of antibody discovery: target selection, lead optimization, humanization, and development
- Proven ability to translate computational research into portfolio impact. You've worked on active drug discovery projects where your work directly influenced decisions, design choices, or project prioritization
- You understand the pressures and constraints of portfolio science: timelines, resource constraints, competing priorities, the need for both speed and rigor
- You know how to communicate uncertainty and limitations to non-expert audiences; you can explain what models can and cannot do
- Experience working across scientific teams and navigating organizational complexity
- Demonstrated track record leading research teams or mentoring junior scientists
- Ability to attract, develop, and retain talented people
- You create clarity around expectations, provide constructive feedback, and invest in people's growth
- Strong communication skills: can present complex science to senior leadership and collaborate across disciplines
- You see where AI/ML can have outsized impact in drug discovery and why some approaches work better than others
- You understand the organizational dynamics of large pharma R&D and how to navigate them effectively
- You're comfortable with ambiguity but disciplined about execution
- You have opinions about how things should work, and you drive toward better approaches
Responsibilities
- Drive portfolio impact by leading the application of machine learning models (developability, functional modeling, design optimization) to active gRED projects—taking models from research to real projects with measurable outcomes
- Interface with gRED leadership as a trusted technical advisor on computational strategy, capability development, and portfolio prioritization; serve as the primary liaison between computational sciences and gRED leadership
- Lead the modeling team (currently 3-4 scientists), setting research direction, mentoring scientific development, and creating an environment where people do their best work
- Develop and execute a technical strategy for how ML shapes gRED's approach to antibody discovery and engineering and align with your pRED counterpart
- Navigate complex stakeholder landscapes, including Antibody Engineering, platform teams, and external partners, to align on priorities and build collaboration
- Identify and own high-impact research initiatives that solve real problems for the portfolio and advance the state of the science
Benefits
- A discretionary annual bonus may be available based on individual and Company performance.
- Benefits detailed at the link provided below.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
Ph.D. or professional degree
