AI Agent Engineer (Controls)
About The Position
This hands-on engineering role blends data science and software engineering. The AI Agent Engineer (Controls) builds agents for Ford’s Agentic Issue Resolution (AIR) system, which helps plant teams investigate and resolve production issues. Agents gather approved evidence from plant systems, connect findings to existing plant knowledge, and recommend fixes for a person to review and approve. The role involves designing how agents plan investigations, select tools and data, and explain their findings. The position works onsite with manufacturing supervisors and engineers at Ford’s Manufacturing Technology Development Center in Redford, Michigan, and includes learning from supervisors and engineers at Kentucky Truck Plant. The work is part of Ford’s Advanced Industrial Technology and Platforms organization, which develops and scales industrial platforms, technologies, and capabilities for manufacturing.
Requirements
- Bachelor’s degree in Computer Science, Data Science, Engineering, Statistics, or a related field, or equivalent experience.
- At least 3 years of experience in data science, machine learning engineering, or software engineering, including production work.
- Experience with Mfg Controls.
- Hands-on experience building with large language models, including prompting, retrieval-augmented generation, tool use, and agent frameworks.
- Strong Python and SQL skills.
- Experience designing experiments and evaluating model or system output.
Nice To Haves
- Experience with agent frameworks such as LangGraph or Google ADK and the Model Context Protocol (MCP).
- Manufacturing, quality, or structured problem-solving experience, such as 8D or 5-Why.
- Knowledge of knowledge graphs or ontologies.
- Experience with Google Cloud Platform and Vertex AI.
Responsibilities
- Build agents that classify issues, plan investigations, call tools, and draft recommendations.
- Design multi-step and multi-agent workflows with clear hand-offs and stopping rules.
- Write and maintain prompts, tool definitions, and retrieval logic.
- Connect agents to production, quality, and maintenance data and to CoreMesh, ATP’s manufacturing ontology and knowledge graph.
- Rank and filter evidence so agents reason from relevant sources, and include those sources in every output.
- Ensure agents flag low confidence or missing data and hand off to a person.
- Test agents against shared evaluation sets before each release and add cases from plant experts.
- Analyze failures, compare approaches, and improve accuracy, cost, and response time.
- Use user feedback and confirmed fixes to improve agent behavior.
- Spend time with supervisors and engineers at Kentucky Truck Plant to understand how production problems are solved.
Benefits
- Immediate medical, dental, vision, and prescription drug coverage.
- Paid parental leave, new parent ramp-up programs, and subsidized back-up child care.
- Family building benefits, including adoption and surrogacy expense reimbursement and fertility treatments.
- Vehicle discount program for employees and family members and management leases.
- Tuition assistance.
- Employee resource groups.
- Paid time off for individual and team community service.
- Vacation time, sick/personal time, and paid holidays, including between Christmas Eve and New Year’s Day.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
