Sr. Data Scientist

We are hiring a Senior Data Scientist to accelerate development of the methods, analyses, and digital workflows that comprise the heart of Sound’s discovery engine for epigenetic traits and agronomic active ingredients. Come help refine the epigenetic methods we use to develop nutritious and resilient crops – far faster than gene editing – and help us optimize our discovery pipeline for active ingredients that sustainably improve crop performance. Our aim is to unleash the power of plants to create a more agile and resilient food system, and we’ve gotten a great start: our product SOURCE, already being used on more than 1 million acres, stimulates already-present soil microbes to fix nitrogen so that farmers need less synthetic fertilizer. We are saving grower costs, boosting yield, and making agriculture more sustainable.

The Senior Data Scientist will help grow the organization as a combination of a hands-on developer, data architect, and expert data science practitioner with authority to make strategic decisions and lead development. The Senior Data Scientist will design, develop, enhance, maintain, and use data architecture including cloud compute services, knowledge discovery platforms, and advanced experimental automation. We currently work across AWS services (S3, Nextflow, docker), on-site genomic data generation (Oxford Nanopore), SaaS LIMS, and ML models running on custom high performance computing, with increasing levels of automation and abstraction. We democratize analysis using custom microservices, jupyter notebooks, and stats/viz packages like JMP. This role will help determine what’s next.

The Senior Data Scientist role reports to the Director, Data Science and will interact with functions across the company as a project and team lead. This role is a hybrid onsite position based in our Emeryville, CA headquarters. 

Responsibilities

• Lead development of core data infrastructure (including both custom-developed and SaaS LIMS) for effective inquiry, ML model building, and visualization which encompasses petabytes of data on 100s of thousands of samples per year.
• Build and deploy software tools to provide streamlined data access (through ETL, REST services, query systems, and off-the-shelf informatics) for stakeholders across Sound Research including scientists, process engineers, the Molecular Foundry team, and ChemBio and On Demand Breeding platforms.
• Collaborate with Research teams to investigate novel aspects of epigenetic control of gene expression through targeted experimental design and advanced modeling.
• Collaborate with Research teams to discover, characterize, and develop novel active ingredients which enhance crop nutrient efficiency through assay optimization, experimental design, and ML models.
• Manage in-house and contractor developers as projects grow
• Champion our in-house data science and software engineering practice. Provide in-depth training on methods, tools, workflows, infrastructure, lifecycle management, and statistical fluency.
• Rapidly prototype data capabilities for grateful research teams to maximize economic and environmental benefits for growers
• Work to reduce work, by systematically improving the quality and maintainability of Sound’s data and data processes.

Target Skills & Experience

• Demonstrated software engineering success, both as a direct contributor and project lead
• Fluency with the data needs of biotech, including automation for molecular biology, genomic data collection and analysis, forward-looking data design, the optimization of discovery pipelines, and democratization of advanced analysis
• Expertise with statistics, visualization, and practical machine learning
• Experience with data lake and warehouse principles, tools, and techniques to create data environments which operate according to F.A.I.R. principles
• Deep fluency with python and at least one other scripting language
• Strong communication skills and the ability to work with experts at varying levels 

This role demonstrates our core values by: 

• Boldness, by rapidly learning, evaluating, and adopting best-in-class tools, methods, and practice in software development and data stewardship
• Ownership, by working closely with teams across Sound Research to deliver meaningful data-driven scientific outcomes
• Respect, by serving as an excellent collaborator across Sound to understand business needs, risks, and opportunities to help us work together better  
• Creativity, by exploring technical and process innovations broadly, even outside our sector, to find and implement the best solutions