AI Systems Engineer

Role Overview

Key Responsibilities

• Design, build, and iterate on agentic AI tools and workflows using orchestration frameworks (e.g., LangChain, LangGraph, CrewAI, AutoGen); deploy production-grade systems used internally and by external users.
• Contribute to the development and external release of AI models and tools into the hands of farmers and agricultural operators.
• Support or lead work on the Velocity Engine depending on team priorities and business needs at time of hire.

• Own end-to-end deployment of AI systems from development through staging to production; ensure systems are reliable, observable, and operationally sound.
• Monitor AI system performance, respond to incidents, and implement improvements in a high-velocity startup environment.
• Collaborate with the Infrastructure & DevOps Engineer to ensure AI workloads are supported by scalable, secure cloud infrastructure.

• Implement evaluation frameworks, testing, and monitoring for AI systems in production; track model performance, cost, and reliability over time.
• Collaborate with AI/ML and product teams on requirements, integration needs, and tooling to accelerate delivery.

Relevant Experience (Ideal Candidate Background)

• Hands-on experience building and deploying agentic AI systems (LLM-based agents, tool use, multi-step reasoning pipelines, RAG, orchestration frameworks) in production environments — or — strong software engineering fundamentals with demonstrated passion for AI and agents. 
• Proficiency in Python and modern AI/ML libraries; experience designing and consuming APIs in production contexts. 
• Familiarity with model deployment, prompt engineering, evaluation, and monitoring in real-world applications. 
• Experience working with cloud platforms (AWS preferred) and containerized (Docker) application deployment. 
• Comfortable operating in ambiguous, resource-constrained startup environments with limited documentation and process. 

What You Bring

• Genuine obsession with AI and agents; you follow the frontier and know what's worth building with. 
• Bias for shipping — you build production systems, not demos or prototypes, and take ownership through deployment and beyond. 
• Ability to operate across internal tooling and external product work; comfortable switching contexts without losing quality. 
• Collaborative yet autonomous working style; excited by breadth and impact over narrow specialization. 

• Startup background with end-to-end ownership of AI product or tooling development. 
• Exposure to agricultural technology, robotics, autonomous systems, or developer platforms. 
• Familiarity with AWS infrastructure (Lambda, ECS, S3, CloudWatch, etc.) in production AI contexts. 
• Open-source contributions that demonstrate ownership — published, maintained, or supported a project.