# AI Engineer **Company**: Ford Motor Company **Location**: Dearborn, MI **Work arrangement**: hybrid **Experience**: senior **Job type**: full-time **Salary**: $99,600-$192,900 **Category**: Engineering **Industry**: Automotive **Wikidata**: https://www.wikidata.org/wiki/Q44294 **Apply**: https://efds.fa.em5.oraclecloud.com/hcmUI/CandidateExperience/en/sites/CX_1/job/73520?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply **Canonical**: https://yubhub.co/job/ai-engineer-ea5c6139-7b3/ ## Description Ford's Industrial Systems Data Platform (ISDP) unifies data from Product Development, Manufacturing, Quality, and Supply Chain applications into a single logical data model. We are building an AI-queryable knowledge graph over that data , a BigQuery property graph derived from a canonical domain event store , and an MCP (Model Context Protocol) server that lets agents reason over it. We are looking for an AI Engineer to own this system end to end: design, develop, test, and deploy the graph layer to Production on a Google Cloud Platform–native stack, and build the agent-facing serving layer on top of it. You will turn raw industrial event data into a governed, traversable graph that powers Ford's next generation of engineering, manufacturing, quality, and supply-chain agents. ## Responsibilities ### Graph Layer - Design, develop, test, and deploy the ISDP knowledge graph from the domain event store to Production using cloud-native data pipelines. - Model and evolve the graph's entities and relationships as new data sources are onboarded. ### MCP serving layer - Design, build, and operate the MCP server that exposes the ISDP graph layer and event store as tools to consumers , including GQL graph query, event-store query, and schema/DDL discovery. - Define tool contracts, context, and guardrails so agents produce grounded, accurate, non-hallucinated responses over the graph. - Ensure low-latency, secure, and cost-efficient serving for interactive and batch agent workloads. ### Reliability, monitoring & observability - Own monitoring and observability of the graph layer and the MCP server , data freshness, pipeline health, query latency/cost, tool-call success rates, and answer quality. - Instrument SLOs, dashboards, alerting, and tracing; drive incident response and continuous reliability improvements. ### Collaboration & data onboarding - Partner with Data Engineers and Application Data Source Owners across Product Development, Manufacturing, Quality, and Supply Chain to ingest and validate their data into ISDP. - Establish data contracts, schema validation, and quality checks; support source owners through onboarding, mapping to the ISDP logical model, and troubleshooting. - Contribute to data governance, cataloging, and lineage for the graph and its sources. ## Qualifications ### Required - 5+ years of experience with Strong software engineering in Java, Python, with production-grade testing, CI/CD, and code quality practices. - 3+ years of experience with Hands-on experience deploying data/AI systems to Production on a GCP-native stack: Vertex AI, BigQuery, Dataflow / Apache Beam, Pub/Sub, Cloud Run / GKE, Cloud Storage, and Cloud Build / Artifact Registry. - 3+ years of experience with graph data modeling and querying , property graphs and GQL / graph query patterns (BigQuery property graphs, or equivalent such as Neo4j/Spanner Graph). - 3+ years of Hands-on experience with Vertex AI (Agents, model serving, embeddings) and evaluation of agent answer quality. - 2+ years of Experience building LLM/agent systems: tool-use, RAG/grounding, and integrating models via APIs (e.g., Vertex AI or enterprise LLM gateways). Familiarity with MCP or comparable agent tool protocols. - Observability expertise: Cloud Monitoring/Logging, OpenTelemetry, SLOs, dashboards, and alerting for data pipelines and services. - 3+ years of experience with Infrastructure as Code (Terraform) and secure-by-default engineering (IAM, least privilege, secrets management). - Ability to work directly with data producers to model and validate real-world industrial/enterprise data. ### Preferred - Familiarity with Dataplex / Data Catalog for governance, lineage, and business glossaries. - Streaming/CDC and event-driven architectures; append-only/event-sourced data modeling. - Design and build user-facing applications and dashboards that surface Knowledge Graph data to end users. - Domain exposure to PLM / product development, manufacturing execution, quality, or supply-chain systems and their data. - Data quality frameworks, schema evolution, and blue-green/zero-downtime data deployments. ## Benefits - Immediate medical, dental, vision, and prescription drug coverage - Paid parental leave, new parent ramp-up programs, subsidized back-up child care and more - Family building benefits including adoption and surrogacy expense reimbursement, fertility treatments and more - Vehicle discount program for employees and family members and management leases - Tuition assistance - Established and active employee resource groups - Paid time off for individual and team community service - Generous vacation time, sick/personal time, and paid holidays, including between Christmas Eve and New Year's Day For more fresh new jobs, check out [yubhub.co](https://yubhub.co/). ## Skills ### Required - Java - Python - GCP - Vertex AI - BigQuery - Dataflow - Apache Beam - Pub/Sub - Cloud Run - GKE - Cloud Storage - Cloud Build - Artifact Registry - Graph data modeling - GQL - MCP - Observability - Terraform - IAM ### Nice to have - Dataplex - Data Catalog - Streaming - CDC - Event-driven architectures - Knowledge Graph - PLM - Data quality frameworks - Schema evolution --- Source: [Apply at efds.fa.em5.oraclecloud.com](https://efds.fa.em5.oraclecloud.com/hcmUI/CandidateExperience/en/sites/CX_1/job/73520?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)