The Role:Septerna is seeking an experienced scientific leader with expertise in AI/ML to lead our Data Science function. The successful candidate will implement advanced machine learning and statistical approaches to leverage Septerna's proprietary GPCR structural and assay data in advancing our small-molecule drug discovery programs.
This is a visionary, hands-on leadership role that requires a strong understanding of our internal data assets, modern drug discovery practices, and advanced computational methods. This leader will create and execute a strategy for fully leveraging Septerna's proprietary data, while collaborating closely with Computational Chemistry, Structural Biology, and other cross-functional research teams to accelerate hypothesis generation and advance scientific discovery.
The ideal candidate brings technical depth in machine learning, practical expertise in statistics, a strong scientific foundation in drug discovery, and the leadership capability to build a high-impact function in a fast-moving environment.
Key Responsibilities- Lead Septerna's Data Science team, providing technical direction, developing team capabilities, and integrating and prioritizing projects, with a primary focus on machine-learning applications.
- Develop and execute a roadmap for implementing state-of-the-art AI/ML approaches that use Septerna's GPCR structural data to discover and refine novel chemical matter.
- Identify productive emerging technologies; lead their integration into Septerna's computational stack through internal development, strategic partnerships, or a combination of both.
- Oversee and extend analysis pipelines, including DNA-encoded library (DEL), high-throughput screening (HTS), and assay-data workflows, and identify opportunities to advance Data Science as part of the broader Platform development team.
- Advance and support ML-QSAR models leveraging internal and external assay and ADMET data to impact the efficiency of DMTA cycles and as a basis for generative chemistry workflows.
- Refine data-engineering and cloud-infrastructure requirements while establishing best practices for data curation and model validation.
Required Qualifications- PhD in computational biology, computational chemistry, or a degree in computer science, applied mathematics or statistics that was focused on modeling biological systems.
- Minimum of 10+ years of relevant industry experience including application of machine learning to diverse scientific problems.
- Demonstrated leadership in machine learning for drug discovery, with a track record of building and applying predictive models to real-world, noisy, and multimodal scientific datasets.
- Experience applying co-folding or hybrid models to enable productive ligand pose prediction ideally on membrane proteins and flexible protein classes.
- Previous work transfer learning or fine-tuning foundation models and using appropriate metrics to demonstrate model performance improvements and characterize applicability domain.
- Experience leading teams and serving as the senior technical lead of cross functional initiatives with track record of applying technical insight and scientific judgement to guide research strategy.
Technical and Platform Requirements- Expertise in scientific machine-learning and drug discovery dependencies such as PyTorch, scikit-learn, numpy, pandas, pyarrow, and RDKit.
- Deep knowledge of modern machine-learning and statistical methods, including gradient boosting decision trees (XGBoost, LGBM), graph neural networks (GNN/D-MPNN), transformers, generative modeling, active learning, and Bayesian optimization.
- Extensive experience with cloud and distributed computing environments, including AWS, GCP, or Azure, as well as building and maintaining containerized machine-learning workflows.
- A strong track record in MLOps and in partnering with software and platform engineering teams to define fit-for-purpose infrastructure for scientific applications.
Preferred Qualifications- Experience with molecular property prediction, generative chemistry, graph neural networks, protein-ligand modeling, sequence modeling, or physics-informed machine learning.
- Hands on structure-based drug discovery and experience collaborating closely with Computational Chemistry teams.
- Publications, patents, or open-source contributions in relevant scientific or machine-learning domains.
The anticipated salary range for candidates who will work in South San Francisco, CA is $240,000 - $300,000. Individual pay may vary based on additional factors, including, and without limitation, job-related skills, experience, work location and relevant education or training. Septerna's compensation package also includes benefits, stock options, and annual target bonus for full-time positions.
