Associate Director - Machine Learning Sciences

Position Summary

The Computational Sciences department drives the use of computation — spanning both AI/ML and physics-based methods — to accelerate and de-risk the Research Portfolio. Within this department, the Machine Learning Sciences team is a small, high-impact group focused on applying machine learning approaches to strengthen predictive capabilities across our small molecule portfolio. The team's work spans ADMET and PK prediction as well as approaches to multiparameter compound design, and it operates at the interface of computational chemistry, medicinal chemistry, DMPK, in vitro biology, and data science.

We are seeking an Associate Director to lead the Machine Learning Sciences team. This is a high-visibility role reporting to the Executive Director of Small Molecule Computational Sciences, with regular exposure to senior leaders across Research. The successful candidate will set scientific direction for the team, manage a small group of talented scientists, and partner closely with portfolio-facing computational scientists, medicinal chemists, DMPK scientists, in vitro biologists, and data scientists to ensure our predictive models achieve the highest possible accuracy and impact on decision-making. Beyond managing the team's current portfolio of work, this leader will be expected to keep the group at the leading edge — continuously evaluating new ML methodologies, algorithms, and external technologies, and bringing the most promising approaches into our predictive workflows.

What You'll Do

• Lead and grow a team of machine learning scientists focused on ADMET/PK prediction and multiparameter design approaches for small molecules.
• Set scientific strategy and priorities for the Machine Learning Sciences team in alignment with broader Computational Sciences and Research goals.
• Partner cross-functionally with portfolio-facing computational scientists, medicinal chemists, DMPK scientists, in vitro biologists, and data scientists to embed ML-driven predictions into project workflows and decision-making.
• Drive continuous improvement in model predictivity through rigorous validation, benchmarking, and iteration against experimental data.
• Scan the external landscape — academic literature, startups, platforms, and emerging technologies — to identify and evaluate new approaches for improving prediction, and lead their assessment and adoption where appropriate.
• Represent Machine Learning Sciences in cross-departmental forums, communicating results, capabilities, and strategy to scientific and senior leadership audiences.
• Mentor and develop team members, fostering a culture of scientific rigor, collaboration, and innovation.
• Contribute to departmental strategy as a member of the Computational Sciences leadership community.

What We're Looking For

We're seeking an experienced, innovative scientist that passionate about the role of computation in drug design. The ideal candidate will bring:

• Advanced degree with experience - (Bachelor's degree with 12+ years of academic/industry experience, OR Master's with 10+ years, OR PhD with 8+ years) in Chemistry, Computational Chemistry, Computer Science, Engineering, or a related field.
• Demonstrated experience applying machine learning methods to chemistry- or drug discovery-relevant problems (e.g., ADMET/PK prediction, property prediction, molecular design).
• A track record of leading teams or projects to productive, measurable scientific impact.
• Strong ability to collaborate across disciplines and communicate complex technical concepts to diverse audiences, including non-computational scientists.
• Demonstrated curiosity and initiative in evaluating and adopting new methods, tools, or technologies.

Preferred Qualifications

• Direct people management experience (supervisory responsibility for scientific staff).
• Experience working within a pharmaceutical, biotech, or similar drug discovery R&D environment.
• Familiarity with multiparameter optimization approaches in small molecule design.
• Experience building or maintaining relationships with external technology providers, academic collaborators, or platform vendors.