2-4 years of engineering experience, particularly with production LLM agents or workflows.
Experience in building agents with tool use, orchestration, context, and memory design.
Strong proficiency in Python and familiarity with PostgreSQL and asynchronous systems.
Ability to write evaluations and critically assess AI-generated code independently.
Familiarity with durable workflow engines and security topics like prompt injection is a plus.
Responsibilities
Design and manage the agent framework, including roles, tools, and task runtimes.
Develop memory and context systems for agents to utilize farm-specific knowledge.
Automate code generation for recurring tasks, ensuring human oversight for anomalies.
Establish evaluations and safety protocols to ensure agent reliability and track improvements.
Integrate machine learning insights into the agent tools on the data layer.
Collaborate with farm teams to observe and enhance the system based on user feedback.
Benefits
Healthcare coverage provided.
Access to AI coding tools, models, and hardware.
1% equity with four-year vesting and a one-year cliff.
Full Job Description
About the Role
Join the founding engineering team building an AI agent framework for farm operations. You will work closely with AI leadership to design and deliver production agents that support real business decisions across multiple farms. What You'll Do
Design and own the agent framework, including roles, tools, permissions, approvals, and a runtime for tasks that span multiple days.
Build memory and context systems that give agents relevant farm-specific knowledge, including information not formally documented.
Develop code automation that enables agents to write and reuse code for recurring tasks, with human oversight for unexpected cases.
Create evaluations and safety measures that make agents reliable for business use and track their improvement over time.
Build agent tools on the data layer and integrate machine learning insights into the framework.
Work with farm teams to observe the system in use and improve it based on feedback.
What We're Looking For
Two to four years of engineering experience, including shipping production LLM agents or agentic workflows that people rely on.
Experience building agents with tool use, orchestration, context and memory design, and evaluation.
Strong Python skills and comfort with PostgreSQL, asynchronous systems, and workflow engines.
Experience writing evaluations and critically reviewing AI-generated code, with the ability to handle system design independently.
Experience with durable workflow engines such as Temporal, agent observability and tracing, or security topics such as prompt injection and permissions is beneficial.
Compensation & Benefits
Base salary is $170,000 to $200,000 annually, plus 1% equity with four-year vesting and a one-year cliff. Healthcare and access to AI coding tools, models, and hardware are provided. Visa sponsorship is not available; candidates must already be authorized to work in the United States. Location
On-site in San Francisco, California, five days per week, with approximately one week of quarterly travel to farms in Washington, Oregon, and California.