Applied AI/ML Software Engineer-Supply Chain AI and Decision Intelligence

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.

Enterprise Technology plays a critical part in shaping the future of mobility. If you’re looking for the chance to leverage advanced technology to redefine the transportation landscape, enhance the customer experience and improve people’s lives, this is the opportunity for you. Join us and challenge your IT expertise and analytical skills to help create vehicles that are as smart as you are.

In this position...

As an Applied AI/ML Engineer in the Supply Chain AI and Decision Intelligence space, you will be the driving force for delivering Ford’s "AI-First" supply chain transformation. This role is focused on the applied implementation of AI: you will develop and deliver the integration of high-performance models (internal or external, e.g., from COTS products) onto Enterprise Knowledge Graphs to solve complex supply chain problems. Central to this role is the adoption of an AI-Driven Software Development Life Cycle (SDLC) leveraging agentic workflows, AI-assisted coding, and automated testing to deliver robust solutions at industrial speed. You will bridge the gap between abstract business problems and scalable technical execution. You aren’t just building chatbots. You are building the intelligence behind a global supply chain, helping the business manage risk, build resilience, and keep factories running. 

This role demands a blend of technical expertise in AI/ML, advanced analytics and data platform engineering, functional expertise in supply chain, and strong technical leadership to influence stakeholders and deliver transformative results. with a particular focus on establishing and standardizing the AI-based SDLC across cross-functional teams.

Based in Dearborn, MI, this is a hybrid position with a required four-day onsite presence each week  Relocation assistance may be available for qualified candidates.

What you'll do...

• Business Requirement Gathering: Partner with supply chain functional leads to elicit and document business requirements and translate them into technical specifications for AI-driven decision support tools, ensuring every solution delivers measurable business value.
• Model Integration & Deployment: Act as the primary technical lead for applied AI implementation. Take pre-developed models from internal partners or 3rd-party vendors (COTS) and successfully deploy them within the supply chain GCP space.
• Graph-Based AI Implementation: Work closely with Knowledge Graph engineering teams to execute model interface against enterprise ontologies, you will design decision-intelligence frameworks that proactively identify and mitigate risks across the global N-tier supplier network. Simulate "what-if" scenarios using Generative AI and Graph analytics, and enable the supply chain to remain resilient against geopolitical, environmental, and logistical shocks, providing automated prescriptive solutions for supply-chain, logistics and capacity re-allocation before disruptions impact production .
• AI-Driven SDLC Execution: Champion and implement AI-assisted development practices. Implement agentic workflows (e.g., AutoGen, CrewAI) and use LLM-based tools (e.g., GitHub Copilot, automated PR agents, and AI-generated documentation) to accelerate delivery with high code quality for the Decision Intelligence platform
• Pipeline & MLOps/LLMOps Engineering: Design the "connective tissue" between Knowledge Graph updates and model inference engines. Establish rigorous guardrail frameworks for toxicity, hallucination rates, and latency. Maintain automated pipelines that ensure decision-support tools are always powered by the most current data. 
• Technical Standardization: Develop reusable integration patterns and data contracts to ensure that AI solutions can be scaled across multiple business units without redundant engineering effort.