Senior Data Scientist / Engineer

Cloudseed Inc is dedicated to solving the problem of global food and water security through the use of Artificial Intelligence (AI) and other emerging technologies. Our mission is to develop tools for consumers and the food industry to accelerate adaptation of land and water practices for a changing climate. Cloudseed Inc is a bootstrapped company. Co-Founders are unpaid during this growth phase. We do this because we think we have a compelling product and we want to help the planet. THIS IS AN EQUITY COMPENSATION ROLE on a Contract Basis. You would be joining the co-founders and the initial founding engineering team of Cloudseed Inc. The position is un-salaried while Cloudseed Inc is raising capital and establishing revenue . Equity is negotiable based on experience and fit. Ideally you are an engineer with extra time minimum 15 hours / week ideally 20 - 40 to devote to a startup in the beginning with the expectation that you'll join full time when the company is funded - equity package will be structured accordingly. We offer an accelerated vesting schedule and a % of company ownership. Overview We’re looking for an experienced Data Scientist to quantify agricultural production risk, water scarcity, and access/affordability across regions and crops. This role combines deep domain expertise in agriculture, hydrology, and risk with advanced data engineering and modeling skills to deliver production-ready insights and tools. Key Responsibilities 1. Quantify Agricultural and Water Risk Analyze production risk, water scarcity, and affordability across geographies and crops. Develop early-warning systems, forecasts, and scenario models to anticipate disruptions and inform decisions. Build and operationalize yield, price, and risk models using time-series, Bayesian, econometric, and ML/DL methods for forecasts, scenarios, and early-warning signals. Implement robust model validation, uncertainty quantification, and performance tracking. Independently collect, ingest, and stage complex datasets (APIs, scrapers, bulk downloads, satellite archives). Build reproducible ETL/ELT pipelines in Python and SQL, including metadata, QC, lineage, and version control. Manage large-scale datasets (TB-level) across formats such as COG, GeoTIFF, NetCDF, Zarr, and Parquet. Core Datasets (Required Expertise) Agriculture: USDA NASS/CDL, farmer-level data, and satellite-derived production metrics. Water & Climate: NOAA, PRISM, USGS, DWR, SMAP, Sentinel, Landsat. Soils: SSURGO, STATSGO, SoilGrids, HWSD; derive attributes like AWC, pH, salinity, texture, and drainage. Insurance & Risk: Loss/trigger frameworks (NDVI/PRF/MPCI), catastrophe curves, basis-risk, and stress tests. Open-Source & Delivery Develop and deliver APIs, notebooks, and dashboards using open-source tools for enterprise and mobile applications. Contribute to reproducible, transparent data science through documentation, governance, and MLOps best practices. Lead high-value, bespoke client analyses and translate findings into actionable insights and SLAs. Define and evolve the organization’s data science vision, standards, and technical roadmap. Required Skills 5–8+ years delivering production data science with agriculture + water datasets (required) and soil datasets (required). Engineering skill set: Independently source, ingest, clean, and stage multi-TB datasets. Comfortable with COG/GeoTIFF/NetCDF/Zarr/Parquet, APIs, web scraping, and batch/distributed processing. Experience: 5–8+ years in production-grade data science working with agriculture, water, and soil datasets. Data Engineering: Ability to source, ingest, clean, and stage multi-terabyte datasets independently. APIs, web scraping, and batch/distributed processing. Technical Stack: Python (required): Production grade scalable data pipelines, ML model training at scale, and analytics workflows. SQL & Postgres/PostGIS: Advanced spatial queries and data management. Proficiency with APIs, web scraping, distributed/batch processing, and geospatial data formats. Cloud-Optimized Geospatial Data Science / Engineering: Comfortable with COG/GeoTIFF/NetCDF/Zarr/Parquet. AWS Cloud Infrastructure knowledge. Time Series Analysis and Forecasting. Spatio-temporal Modeling and Geostatistics. Classical & Modern ML Methods (Random Forests, XGBoost, Gradient Boosting, SVMs). Bayesian Inference and Probabilistic Modeling. Global Data Operations: Operationalize global datasets; Handle CRS/ellipsoids, multilingual data, time zones, units, currencies, and privacy compliance (GDPR), and global refresh/versioning cadence. Communication: Excellent ability to translate technical insights for executives, engineers, and non-technical audiences. Preferred Qualifications Remote sensing (Landsat/Sentinel/VIIRS), feature engineering from COG/Zarr. Crop models (APSIM/DSSAT) and climate scenarios (CMIP6/SSPs). What You’ll Learn Agricultural domain expertise and crop modeling algorithms Large-scale geospatial data processing techniques AI/ML applications in agriculture and conversational interfaces Production scientific computing and optimization strategies Startup culture and growth strategy and emphasis navigating an environment of pivots with an emphasis on cash flow and technical leadership opportunities Level Senior (4-7 years experience) - High impact role with growth potential as we scale our platform and team. Cloudseed is an Equal Opportunity employer committed to diversity in the workplace. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, age, national origin, disability, protected veteran status, gender identity or any other factor protected by applicable federal state or local laws. Cloudseed is also committed to working with and providing reasonable accommodations to individuals with disabilities. Privacy is a top priority for Cloudseed. We build it into our products and view it as an essential part of our business. #J-18808-Ljbffr CloudseedAi