Sr. Data Scientist

We are looking for an experienced data scientist to empower our medical diagnostic capabilities. As an integral part of our R&D, you will be called on to research and develop data-centric analytic methods. The successful candidate will be in charge of researching and developing algorithmic pipeline across various system levels, from raw genomic data processing, through features extraction up to machine learning, statistical assessment and optimization.  

The successful candidate will be an essential team player for significant optimization of our growing genomic data analytic platform. This entails working cross-functionally with bioinformaticians, clinical analysts, software engineers and business analysts to ensure Veracyte's data becomes powerful asset and value growth driver. Specifically, the role assumes participation in the design and prototyping of cutting-edge deep learning, machine learning and statistical algorithms for analysis of genetic data to improve clinical performance, hacking the high-throughput data processing pipelines - to replace heavy repetitive computations with trained models, and utilize DL/ML on a system level to shorten the processing times and costs. 

The ideal candidate will have the ability to see the big picture and to understand user needs and requirements and to identify the opportunities for applying solutions from the deep learning, machine learning, algorithms and data science domains. 

Responsibilities 

• Conduct advanced analyses of next-generation sequencing data, from individual research experiments to very large-scale datasets.
• Research, design, and implement novel deep learning architectures, statistical algorithms, and mathematical models to advance applications in genomics.
• Contribute to the design and development of data specification standards and scalable data science processes, ensuring consistency and reproducibility.
• Derive robust and correct conclusions grounded in rigorous mathematical analysis and principles of probability and statistics.
• Collaborate closely with R&D, production, and clinical teams to develop and optimize pipelines for high-throughput sequencing data.
• Act as a subject matter expert for data- and algorithm-related issues, providing guidance and troubleshooting support.
• Ensure internal processes, metrics, and workflows align to deliver the highest product quality and scientific rigor.
• Develop and maintain Python-based software infrastructure to support algorithm testing, benchmarking, and simulation studies.
• Prepare clear, concise, and accurate technical documentation, including research reports, algorithm specifications, and data standards.
• Partner across the organization to design and implement end-to-end data application pipelines for large-scale sequencing workflows.
• Proactively identify opportunities to improve existing technology and contribute ideas that drive innovation and future product development.

Who You Are:

• Master's degree / PhD in engineering, computer science, bioinformatics, statistics, or similar, with a strong foundation in probability theory and/or statistics.
• A minimum of 6 years of practical experience in scientific methods, processes, algorithms and systems for knowledge and insights extraction from data
• Extensive knowledge in the domains of machine learning, signal processing and related quantitative techniques and theory
• Strong foundation in probability theory and/or statistics including parameter estimation and hypothesis testing
• Knowledge of core concepts in data analysis and applied statistics - model testing, regression, classification, clustering, data mining
• Good Python, bash and scripting fundamentals, including file parsing and data visualization
• Experience with cloud computing technologies (AWS preferred) - a plus
• Proficiency in at least one major deep learning framework (PyTorch, TensorFlow, MXNet) – a plus
• Knowledge of bioinformatics tools, clinical diagnostics workflows or genetic processes - a plus
• Experience with data management in a regulated environment - a plus
• Desire to learn about human genetics, genomics and next-generation sequencing technologies
• Highly organized and detail-oriented, with the ability to create clear and concise technical documentation
• Excellent verbal and written communication skills and the desire to work in a dynamic and collaborative environment
• Ability to work independently and remotely while maintaining a strong teamwork ethics

Key attributes 

• Independent self-management and organizational skills
• Able to manage workload and set personal and project priorities
• Entrepreneurial, driven to create and to be impactful team player
• Relies on data more than gut instinct
• Puts the team harmony over their own self-interest, but data above all
• Strong attention to detail demonstrating accuracy in tracking and reporting data
• Flexibility to adjust quickly and effectively to frequent change and altered priorities
• Disciplined in following process consistently
• Eagerness to acquire new skills in areas such as databases, statistics, and genetics
• Excellent verbal and written communication
• Ability to evaluate and apply new technologies in a short time

#LI-Hybrid