Data Scientist III

The Position:

This is a remote friendly position. On-site cube available in South San Francisco or San Diego.  

We are seeking a talented and experienced AI/ML data scientist to join our Veracyte’s Data Science team. This position offers a unique opportunity to work with experienced professionals to drive research and develop new diagnostic products employing one of the world’s largest clinical cancer databases, encompassing multi-platform digital pathology, genomic and clinical outcome data.    

The successful candidate will develop digital pathology AI models for a wide range of clinical and pathology outcomes by applying and adapting state-of-the-art vision/vision-language foundation models to whole-slide images (WSIs). As a Data Scientist III at Veracyte, the candidate will be expected to assist in developing innovative solutions to complex problems under company’s objective. This work will be conducted in close collaboration with other teams, including internal medical and business development teams, as well as key opinion leaders, with whom we collaborate on identifying relevant data, and developing computer vision models. The ability to explain AI/ML concepts to both experts and non-experts, including formal presentation, academic writing, and generation of publication-quality figures will be key necessary talents. The ideal candidate is passionate about data, eager to learn independently, and possesses strong analytical, problem-solving, and storytelling skills.   

 KEY RESPONSIBILITIES:  

• Develop digital pathology AI (DPAI) models with WSI data to predict clinical outcome and pathological/morphologic features, including adapting open-source state-of-the-art AI foundation models to Veracyte’s data.  

• Evaluate and analyze DPAI models with respect to clinical, pathological and genomic outcomes or features, with a view to linking explainability of model features to biology. 

• Design and carry experiments to compare and evaluate DPAI methods. Document and explain the results. 

• Collaborate with both internal and external partners to understand the clinical and business requirements for given products and tailor algorithms accordingly.  

•  Work with bioinformatician, statistician, and medical experts to document projects, including generating analyses and visualizations for publication in peer-reviewed journals.  

Who You Are:

REQUIRED EXPERIENCE:    

• PhD in Data Science, Machine Learning, Applied Math or equivalent field.   

• 5+ years of experience of data/applied scientist role or equivalent  

• Expert in Python or equivalent language for AI/ML development in the context of computer vision / DPAI (this includes data manipulation and preparation.) 

• Experience in statistical analysis, especially in survival modelling and hypothesis testing (i.e., multivariate regression modelling with interaction effects). 

• Experience working in cloud computing environments (AWS preferred).   

• Demonstrated proficiency in summarizing and communicating findings from data, including an attention to detail when sharing findings. 

• Ability to work effectively in a fast-paced and collaborative environment.  

• Eagerness to learn new technologies and adapt to evolving requirements.   

RELEVANT EXPERIENCE (preferred but not required):      

• Knowledge of cancer biology 

• Proficiency with documentation and submission in regulated diagnostic environments (LDT or IVD). 

• Experience working with real world clinical data. 

#LI-Hybrid, or #LI-Remote