2-4 years of engineering experience with production pipelines or messy data integrations.
Strong proficiency in Python and SQL, with experience in PostgreSQL and data warehousing tools like BigQuery.
Experience designing schemas for dependency and resolving production issues.
Daily engagement with AI technologies and understanding their limitations.
Familiarity with data quality frameworks and evaluation processes.
Background in connector frameworks like Airbyte or Fivetran, and experience with ERP, IoT, or agriculture data.
Responsibilities
Build a reusable connector framework for faster customer integrations.
Develop a reliable AI-assisted process for creating connectors using vendor documentation.
Create data access methods for systems lacking APIs, including server-based collectors.
Design and maintain a canonical farm data model with pre-implementation reviews.
Own tools for data quality assessment and failure diagnosis.
Build querying tools for agents and prepare machine learning training datasets.
Occasionally work on-site to connect farm systems.
Benefits
Healthcare coverage provided.
Access to AI coding tools and models.
Necessary hardware supplied.
1% equity with four-year vesting and a one-year cliff.
Full Job Description
About the Role
Build the data infrastructure for an agentic operating system serving farms. You will create reliable ways to bring information from disconnected farm systems into a unified platform, enabling product agents and insights to work with consistent, trustworthy data. What You'll Do
Build a connector framework that makes integrations reusable and faster to configure for new customers.
Develop a reliable process for AI-assisted connector creation using vendor documentation.
Create ways to access data from systems without APIs, including collectors that run on farm servers.
Design and maintain a canonical farm data model, with proposed mappings reviewed before implementation.
Own data quality and evaluation tools to detect and diagnose failures.
Build tools for agents to query data and prepare machine learning training sets.
Occasionally work on-site to connect farm systems.
What We're Looking For
Two to four years of engineering experience building and operating production pipelines or integrations with messy data sources.
Strong Python and SQL skills, plus experience with PostgreSQL, a data warehouse such as BigQuery, and tools such as dbt.
Experience designing schemas that other people and systems depend on, and resolving production issues directly.
Daily experience building with AI and a practical understanding of its limitations.
Experience with data quality and evaluation frameworks.
Helpful background includes Airbyte, Fivetran or similar connector frameworks; document extraction or OCR; and data from ERP, IoT, agriculture, logistics, or food supply chain systems.
Compensation & Benefits
Base salary is $170,000 to $200,000 annually, plus 1% equity with four-year vesting and a one-year cliff. Healthcare, AI coding tools and model access, and necessary hardware are provided. Visa sponsorship is not available; candidates must be authorized to work in the United States. Location
On-site in San Francisco, five days per week. The role includes approximately one week per quarter visiting farms in Washington, Oregon, and California.