AI Agent Engineer; Controls
-
Software Development
Job Description & How to Apply Below
We made history and now we work to transform the future – for our customers, our communities and our families. You'll see your work on the road every day, helping people move freely and pursue their dreams. At Ford, you can build more than vehicles. Come build what matters.
Shape the Future of Manufacturing with ATP
At Ford, we aren’t just building vehicles — we are redefining how the world moves. Within the Advanced Industrial Technology and Platforms (ATP) organization, we are the architects of Ford’s next industrial revolution.
Our mission is clear: we build and scale industrial platforms, technologies, and capabilities that unlock Ford Firsts to drive sustained competitive advantage in manufacturing. Driven by our vision to 'build once, scale everywhere,' we bridge the gap between cutting-edge technology and global physical deployment.
Our guiding mantra is simple yet relentless:
Scale what matters, win what's next.
If you are a high-tech builder, thinker, or innovator who thrives at the intersection of software, hardware, and massive scale, ATP is where you belong. Join us, and write the next chapter of industrial history.
In this position...This is a hands-on engineering role that blends data science and software engineering.
Plant problems rarely have one obvious cause. Our answer is AIR (Agentic Issue Resolution), ATP's AI system that helps plant teams investigate and fix production issues. AI agents take an issue, gather approved evidence from plant systems, connect it to what the plant already knows, and recommend a fix that a person reviews and approves.
As an AI Agent Engineer (Controls), you build those agents: how they plan an investigation, which tools and data they use, and how they explain what they found. You will work on site at Ford's Manufacturing Technology Development Center (Redford, MI) with the supervisors and engineers who use what you build.
What you'll do... Build and Orchestrate Agents- 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 Core Mesh, ATP's manufacturing ontology and knowledge graph, which gives plant data one shared meaning across systems and plants.
- Rank and filter evidence so agents reason on the right sources, and show those sources in every output.
- Have agents flag low confidence or missing data and hand off to a person.
- Test agents against the shared evaluation sets before each release, and add cases from plant experts.
- Analyze failures, compare approaches, and improve accuracy, cost, and response time.
- Turn user feedback and confirmed fixes into better agent behavior.
- Spend time with supervisors and engineers at Kentucky Truck Plant to see how problems really get solved.
- Agents complete investigation steps reliably, with sources shown and confidence stated.
- Evaluation results improve release over release.
- Supervisors and engineers act on the recommendations and confirm fixes.
- Bachelor's degree in Computer Science, Data Science, Engineering, Statistics, or a related field, or equivalent experience.
- At least 6-8 years' 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: prompting, retrieval-augmented generation, tool use, and agent frameworks.
- Strong Python and SQL.
- Experience designing experiments and evaluating model or system output.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).
View / Apply for Jobs
Matching My Jurisdiction