As the first machine learning engineer on a founding team at an agricultural technology company, you will build the core insight engine for an operations platform serving growers. You will turn fragmented farm data into carefully evaluated models that help inform important operational decisions.
Audit and integrate historical data from farm systems, identifying useful signals and gaps.
Build machine learning tools for forecasting, performance analysis, and operational efficiency.
Develop backtesting and evaluation frameworks to validate model accuracy before deployment.
Create privacy-first datasets that enable farms to benefit from pooled insights.
Collaborate with an agent engineer to present actionable insights through the product.
Qualification
Strong Python and SQL skillsRigor in model evaluation
Required
Two to four years of engineering experience, including ownership of meaningful projects and production ML models used to inform decisions.
Strong Python and SQL skills, with experience in pandas or Polars, scikit-learn, gradient boosting, and forecasting libraries.
Experience with tabular or time-series data, data pipelines, or tools that help explain model behavior.
Rigor in model evaluation, including awareness of data leakage, backtesting, and production readiness.
Ability to communicate model outputs and uncertainty to non-technical stakeholders.
Regular use of AI tools and interest in combining LLMs and agents with classical machine learning.
Experience with large-scale or messy startup data is useful. Agriculture, weather, supply chain, physical-world forecasting, or privacy-preserving data experience is a plus.