Join Ford’s Industrial Systems Data Platform (ISDP) team to build an AI-queryable knowledge graph and an agent-facing serving layer on a Google Cloud Platform-native stack. This hybrid role in Dearborn, MI helps turn industrial event data into a governed, traversable graph that supports engineering, manufacturing, quality, and supply-chain agents.
What you’ll be building
You will design, develop, test, and deploy the ISDP graph layer to Production, then operate an MCP (Model Context Protocol) serving layer that exposes the graph and event store as tools for consumers. The work includes supporting GQL graph query, event-store query, and schema/DDL discovery, along with tool contracts and guardrails to help agents generate grounded, accurate, non-hallucinated responses.
Responsibilities
- Own the system end to end: design, develop, test, and deploy the graph layer to Production on a GCP-native stack, and build the agent-facing serving layer on top.
- Design, develop, test, and deploy the ISDP knowledge graph from the domain event store to Production using cloud-native data pipelines.
- Model and evolve graph entities and relationships as new data sources are onboarded.
- 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.
- Own monitoring and observability for the graph layer and 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.
- Partner with Data Engineers and application data source owners across Product Development, Manufacturing, Quality, and Supply Chain to ingest and validate 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.
Requirements
- Bachelor’s Degree in Computer Science, Information Technology, or Engineering (or equivalent combination of education and experience).
- 5+ years of experience with strong software engineering in Java and Python, including production-grade testing, CI/CD, and code quality practices.
- 3+ years deploying data/AI systems to Production on a GCP-native stack, including Vertex AI, BigQuery, Dataflow / Apache Beam, Pub/Sub, Cloud Run / GKE, Cloud Storage, and Cloud Build / Artifact Registry.
- 3+ years of graph data modeling and querying experience, including property graphs and GQL / graph query patterns (e.g., BigQuery property graphs or equivalent such as Neo4j / Spanner Graph).
- 3+ years hands-on with Vertex AI (Agents, model serving, embeddings) and evaluation of agent answer quality.
- 2+ years building LLM/agent systems: tool-use, RAG/grounding, and integrating models via APIs (e.g., Vertex AI or enterprise LLM gateways), plus familiarity with MCP or comparable agent tool protocols.
- Observability expertise including Cloud Monitoring/Logging and OpenTelemetry, with SLOs, dashboards, and alerting for data pipelines and services.
- 3+ years 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.
Technologies
Java, Python, Vertex AI, BigQuery, Dataflow, Apache Beam, Pub/Sub, Cloud Run, GKE, Cloud Storage, Cloud Build, Artifact Registry, GQL, Neo4j, Spanner Graph, OpenTelemetry, Terraform, IAM.
Benefits
- Immediate medical, dental, vision and prescription drug coverage
- Flexible family care days, paid parental leave, new parent ramp-up programs, subsidized back-up childcare 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
- A generous schedule of paid holidays, including the week between Christmas and New Year’s Day
- Paid time off and the option to purchase additional vacation time
Location and work type
- Dearborn, MI (hybrid)
- Hybrid role with a requirement to be onsite four or more days per week
- Job type: Full time
- #LI-Hybrid, #LI-PW1
Salary range
$99,600 - $192,900 per year (range of salary grades 7-8). Final determination depends on skills, experience, job scope, responsibility, and competitive market value.
Preferred qualifications
- 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
Visa sponsorship and authorization
- Visa sponsorship is available for this position.
- Domestic relocation is not available for this position.
- Candidates must be legally authorized to work in the United States; verification of employment eligibility will be required at hire.
- Ford Motor Company is an Equal Opportunity Employer.
- Reasonable accommodation for the online application process due to a disability: call 1-888-336-0660.
Domain you’ll master
Ford’s Industrial Systems and the ISDP logical data model, including how Product Development, Manufacturing, Quality, and Supply Chain applications describe programs, parts, ECUs, sites/plants, suppliers/organizations, requirements, verifications, quality problems, and warranty/returns, plus how these entities interconnect in the knowledge graph.
