Principal Data Scientist - Arable

Job Title: Principal Data Scientist
Job Location: San Francisco Bay area
Job Listing URL: https://jobs.lever.co/arable/56af9a20-249b-4f17-8a58-f5f3e9e13fbc
Job Description: Come work alongside some of the most talented minds in the agtech industry. We are a team of innovators who are accelerating the digitization and sustainability of our planet’s food system. At Arable, you will have the unique opportunity to build something meaningful with an amazing group of people who care about each other and their work.

What we do:

At Arable, our goal is to connect all the world’s farms to help optimize the global food system. This is an ambitious goal, but the need has never been greater to rethink how we will feed an ever-growing population and reduce our impact on natural resources. We believe the heart of the solution is digitizing the analog world with high-fidelity data to help food producers optimize their operations. We hope the impact of our work will improve the lives of farmers everywhere and be a major contribution to securing the global food supply for decades to come.
A few examples of the work we’re doing today:

Helping farmers in India and Mozambique adapt to the effects of climate change on their farms with novel data-driven crop insurance
Giving produce growers in California the tools to optimize production and minimize waste
Helping irrigated farms in Nebraska manage water more efficiently and sustainably to protect our water supply

What We're Looking For:
Arable Labs seeks an experienced and insightful Principal Data Scientist to join our mission-driven team, reporting to the Head of Data Science. Our work leverages unique, high-fidelity field data to provide critical insights for global agriculture and environmental monitoring. In this key role, you will apply your deep expertise in machine learning, statistical modeling, and software engineering to solve complex challenges in agricultural water management. You will lead the development of core predictive models, drive innovation through applied research, and see your work contribute directly to farm sustainability and resource efficiency, often supported by broader corporate environmental initiatives. We need a hands-on technical leader passionate about tackling meaningful problems and translating data into real-world impact.
Where You'll Make an Impact:
Significantly improve models that help farmers optimize irrigation, conserve water, and understand field conditions (e.g., rainfall, evapotranspiration, water balance).
Advance Arable's predictive capabilities through the application of novel ML techniques and sensor data analysis.
Contribute directly to tools supporting climate resilience and sustainable practices in agriculture.
What You Will Do:
Lead End-to-End Model Development: Drive the full lifecycle of core machine learning models – from research, prototyping, and validation to deployment (Python, Docker, Flask, AWS/SageMaker) and ongoing performance monitoring and improvement. Key areas include water balance, ET, rainfall, and irrigation insights.
Conduct Applied Research & Innovation: Identify opportunities and execute applied R&D projects to enhance model accuracy, leverage new data sources (internal sensor streams, external weather data), and develop novel predictive features, balancing exploration with pragmatic delivery.
Collaborate for Impact: Work closely with cross-functional teams – Product (defining requirements, translating features), Sensors/IoT (understanding data, calibration and validation), and Software (API integration, production pipelines) – to ensure data science solutions effectively meet business and user needs.
Ensure Solution Quality & Provide Expertise: Uphold high standards for model performance and data integrity through rigorous validation, anomaly detection, and addressing operational analytical needs. Serve as a subject matter expert in your domain areas and contribute to the team's technical strategy and best practices, potentially mentoring junior members.
Required Experience and Skills:
MS or PhD in a quantitative field or equivalent deep practical experience.
5-8+ years relevant hands-on experience developing & deploying ML/DS solutions.
ML & Statistical Depth: Strong theoretical understanding and practical expertise in machine learning (especially time-series), statistical modeling, and validation techniques.
R&D Acumen: Demonstrated ability to conduct applied research, tackle ambiguous problems, and deliver impactful, data-driven solutions.
Technical Implementation: Proficiency in Python for data science (NumPy, pandas, scikit-learn, etc.), strong software engineering practices (Git, testing, docs), and experience deploying models via APIs (Flask) using containers (Docker) on cloud platforms (AWS).
Communication & Collaboration: Excellent ability to communicate complex concepts clearly and collaborate effectively within a cross-functional environment.
Preferred Experience and Skills:
Domain Knowledge: Background or strong interest in agriculture, hydrology, meteorology, soil science, or related environmental sciences.
Sensor Data & Techniques: Experience with real-world IoT sensor data (including CalVal), anomaly detection, and leveraging external datasets (weather, geospatial).
Startup Environment: Proven ability to thrive and take ownership in a fast-paced, dynamic startup setting.
AWS ML Ecosystem: Deep familiarity with AWS services, particularly SageMaker.
Mentoring: Experience guiding or mentoring other technical team members.