Sr. Data Scientist

Trace Genomics has developed the first analytics engine that learns as it maps the living soil. Founded in 2015 to serve the farming community, Trace Genomics helps growers maximize the value of every acre. The company is building the largest, most actionable body of soil intelligence, making thousands of growers experts on what’s underground. Working collaboratively across the agriculture ecosystem, Trace Genomics helps growers optimize costs, manage risk and protect their soil. Headquartered in Silicon Valley—led by industry veteran Dan Vradenburg and founded by two female PhDs from Stanford University—Trace Genomics is having a meaningful impact on the future of food.
At Trace Genomics, our goal is to leverage our unique data on the soil environment to provide new tools for agriculture to solve important problems. Our database is composed of information on the microbial, chemical, and physical attributes of soil, one of the most complex habitats on the planet. This data can inform solutions to challenges facing agriculture today, from the need to grow crops more sustainably to the uncertain effect of new products on crop health. We are hiring a Senior Data Scientist with deep expertise in machine learning, statistics, building data products, and data tools to expand our ability to apply data to solve problems facing agriculture. You will work with a science and analytics team that is responsible for a wide range of challenging problems including, but not limited to, bioinformatics, machine learning, statistics, customer analyses, and product evaluations.
Responsibilities: Lead and enhance Trace Genomics’s predictive capabilities by: ●      Extracting new features from our unique soil and microbiome data layers;●      Identifying and guiding development of products that leverage statistics and/or state of the art machine learning based methodologies;●      Designing, optimizing, and deploying scalable machine learning based tools into production;●      Evaluating and optimizing existing machine learning processes; and●      Collaborating with engineering and commercial teams to employ best coding practices and to understand customer needs Requirements: ●      Masters or PhD in a quantitative or statistical science●      4+ years of work experience after degree, with demonstrated solid data science knowledge and practice, emphasizing the implementation of machine learning tools in production●      Expertise in machine learning: classification, regression, boosted decision trees (e.g. scikit-learn, XGBoost, LightGBM, etc.)●      Experience with data munging, feature extraction and engineering, data pipeline development and optimization●      Fluency in Python with the ability to read, write, and debug code●      Demonstrated ability to take ownership of significant projects that guide company product development●      Ability to independently interpret signals and draw meaningful conclusions from data●      Ability to communicate well in a multi-disciplinary team of scientists and engineers●      Ability to collaborate on vertical (cross-functional) teams to tackle high-visibility, high-value business opportunities Nice to Haves: ●      Experience with geospatial data, including agricultural data layers●      Experience with accessing public APIs and building tools to incorporate new data layers, e.g. satellite imagery, climate data●      Experience with genomic and/or microbiome datasets●      Experience with Bayesian modeling (e.g. PyMC3)●      Experience with PyTorch, Tensorflow, or other deep learning packages●      Experience with relational databases●      Experience with data visualization and associated toolsKey Personal Attributes Include:Committed to our core values: Customer-Driven, Scientific Integrity, Creative Problem Solving, Diversity & Inclusion, and Fearless Determination