Scientist / Senior Scientist, Product R&D

Full-time - Entry Level

Sunnyvale, CA

Chemical Manufacturing

About the position

Are you passionate about developing computational methods that directly improve people's lives? Would you enjoy leveraging machine learning, AI, and probabilistic modeling to derive meaningful human health insights from the world's largest database of genetic and phenotypic data? We're looking for an enthusiastic scientist with a background in computational biology or a similar field to contribute to developing 23andMe's consumer product. At 23andMe, our mission is to help individuals and researchers access, understand, and benefit from the human genome. Since 2006, we have been at the forefront of using human genetics to advance biomedical research and transform healthcare, powered by a passionate team and the one of the world's largest genetic databases, with more than fifteen million genotyped customers.

Responsibilities

• Your work will be the scientific foundation of 23andMe customer features
• Build the most comprehensive and accurate prediction models of health outcomes and mortality by leveraging the world's largest genetic and phenotypic database
• Help people live longer and healthier lives by applying state of the art computational biology and/or statistical genetics methodologies to build personalized and compelling recommendation systems
• Deepen our understanding of the human genome beyond genome-wide association studies and polygenic risk scores by integrating biomarkers and clinical data into our predictive models
• Translate academic research into groundbreaking consumer products and features that solve real health problems
• Collaborate with dedicated machine learning engineers to continuously develop our statistical genetics and machine learning software infrastructure
• Keep abreast of the latest scientific studies and advocate for bringing novel methodologies in-house

Requirements

• A Ph.D. degree or equivalent work experience in a quantitative discipline, such as computational biology, bioinformatics, genetic epidemiology, engineering, mathematics, statistics, physics, or computer science
• Familiarity with human biology and/or human genetics (e.g., through working on projects with a disease focus) and/or population genetics
• Strong knowledge of statistics, including Bayesian inference, and its application to designing algorithms
• Expertise and hands-on capabilities with data analysis, programming, and related concepts in Python, including working with packages such as PyTorch and NumPyro
• Motivation to clearly document and communicate your work, including presenting clear descriptions of your technical work to broad audiences and collaborating on coding projects
• A proactive, thorough, and independent work style, along with the ability to thrive in a dynamic, fast-paced, and interdisciplinary team
• A passion for making science accessible and relevant to everyone

Nice-to-haves

• Ideally 3+ years of post-PhD relevant work experience with machine learning, probabilistic modeling, or statistical tools, including designing, implementing, and validating models
• Experience with genome-wide association studies and developing polygenic risk scores
• Experience working with various neural network architectures, using both structured and unstructured multi-modal data
• Experience with algorithm development and implementation
• Experience creating web applications using frameworks (e.g., Django and Flask)
• Experience communicating complex scientific concepts to a non-technical or consumer audience