Data Retrieval Engineer

Ford • Redford Charter Twp, MI,US

12h • $85,400 - $192,900 • Hybrid

About The Position

Ford is seeking a hands-on engineer in its Advanced Industrial Technology and Platforms organization to build enterprise data connectivity and retrieval capabilities. The role develops reusable algorithms, architecture, connectors, ingestion frameworks, and onboarding tools that make data sources quick to connect, discover, and query. It focuses on choosing data representations and retrieval approaches suited to diverse sources, and benchmarking them against real workloads for predictable performance at scale.

The engineer designs graph and relational models spanning manufacturing domains; implements indexing and query execution strategies; and optimizes the full path from source connection through ingestion, indexing, discovery, and retrieval. The platform must integrate metadata catalogs, schema registries, lineage, data quality checks, access controls, and governance. The role also establishes service-level objectives and production observability, deploys and operates services on Google Cloud, and enables global rollout of successful capabilities.

The position includes building AI-driven self-service connector creation with governed review and deployment workflows, and developing retrieval infrastructure for AI consumers through embedding pipelines, vector and hybrid search, and graph-aware retrieval. It also involves evaluation of AI-assisted onboarding and retrieval quality, technical leadership through design and code reviews, and roadmap collaboration with data producers, analytics teams, and AI/ML teams.

The position is hybrid, with a requirement to be onsite four or more days per week. Ford offers salary ranges by grade: grade 6, $85,400–$143,200; grade 7, $99,600–$166,600; and grade 8, $115,000–$192,900. The final grade and salary depend on skills, experience, role scope, responsibility, and market value. Visa sponsorship is available; candidates must be legally authorized to work in the United States.

Requirements

• Bachelor's degree in a related field or equivalent practical experience, with 5–7+ years stated.
• Professional experience building and operating production data platforms, data infrastructure, or backend systems.
• Strong programming skills in at least one systems or data language such as Python, Go, or Rust, and a track record of shipping maintainable, tested code.
• Experience building reusable connectors, ingestion frameworks, or self-service source-onboarding capabilities, including software operated directly by non-platform users.
• Production experience with graph databases, graph processing frameworks, or graph query languages such as Spanner Graph, Neo4j, TigerGraph, GQL, Cypher, Gremlin, or SPARQL.
• Experience with relational and columnar systems, document or key-value stores, search indexes, time-series platforms, or vector retrieval systems; examples include BigQuery, Spanner, AlloyDB, Cloud SQL, Bigtable, Firestore, Milvus, and Vertex AI Vector Search.
• Knowledge of indexing approaches such as adjacency indexes, B-trees, LSM trees, inverted indexes, bitmap indexes, and approximate nearest-neighbor indexes, and experience using profiling and benchmarking to drive measurable performance improvements.
• Experience with metadata catalogs, schema registries, lineage, data discovery, or federated data-product platforms.
• Familiarity with cloud infrastructure, Kubernetes, observability platforms, and infrastructure-as-code; hands-on Google Cloud Platform experience including GKE, IAM, Cloud Monitoring and Logging, and Terraform is expected.
• Experience in automotive, manufacturing, engineering, supply chain, or another complex, data-intensive environment.
• Practical experience applying AI coding assistants and agentic tools to specific engineering workflows, with the ability to verify their output.

Nice To Haves

• Master's degree in Computer Science, Data Engineering, or a related field.
• Experience with streaming and change-data-capture pipelines such as Pub/Sub, Dataflow, Datastream, Kafka, or Flink for near-real-time ingestion.
• Experience with industrial data sources and protocols such as OPC UA, MQTT, historians, or MES and PLM systems.
• Experience building AI/ML retrieval infrastructure on Vertex AI, including embedding pipelines, vector search, hybrid search, or retrieval-augmented generation.
• Experience applying large language models to data engineering tasks such as schema inference, entity resolution, data mapping, or automated data quality checks.
• Experience shipping AI-powered developer or data tools to end users, including code-generating agents, low-code integration builders, or natural-language-to-pipeline products, with human review, sandboxing, and deployment guardrails.
• Experience building or integrating with agent frameworks and tool-use protocols such as Model Context Protocol, or exposing data platforms as tools for AI agents.
• Experience designing evaluation frameworks for LLM-based systems, including retrieval quality metrics and regression testing.
• Experience with query engines and open table formats such as BigQuery, BigLake, Dataproc and Spark, Trino, or Apache Iceberg.
• Experience designing data products or APIs consumed by multiple teams across a large enterprise.
• Strong written and verbal communication skills, including the ability to explain architectural trade-offs to non-technical stakeholders.

Responsibilities

• Design and build reusable connectors, ingestion frameworks, and self-service tools for registering, profiling, and querying new data sources through configuration.
• Model relationships across manufacturing domains using graph and relational schemas.
• Select and implement indexing strategies and query execution paths that meet latency and throughput targets as data volumes grow.
• Profile, benchmark, and tune the complete data path from source connection through ingestion, indexing, discovery, and retrieval.
• Integrate metadata catalogs, schema registries, and lineage tracking so connected sources are discoverable, documented, and traceable.
• Embed data quality checks, access control, governance policies, and lineage capture into ingestion and retrieval workflows.
• Define service-level objectives for retrieval latency, freshness, and onboarding time, and implement observability using Cloud Monitoring and Cloud Logging.
• Deploy and operate the platform on Google Kubernetes Engine and Cloud Run using Terraform; support it in production and resolve root causes.
• Design capabilities for global rollout without re-engineering.
• Use AI coding assistants and large language models for suitable engineering tasks, with validation and engineer review.
• Build product experiences, APIs, and agent workflows for governed, AI-assisted connector creation and deployment.
• Build AI retrieval infrastructure, including Vertex AI embedding pipelines, hybrid search across Vertex AI Vector Search and BigQuery, and graph-aware retrieval.
• Create evaluation harnesses and benchmarks for AI-assisted onboarding and retrieval, measuring precision, recall, and latency against real workloads.
• Set technical direction for connectivity and retrieval; author design documents and lead code and design reviews.
• Partner with data producers, analytics teams, and AI/ML teams to translate access patterns into platform priorities.

Benefits

• Immediate medical, dental, vision, and prescription drug coverage.
• Flexible family care days, paid parental leave, new parent ramp-up programs, and subsidized back-up child care.
• 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.
• Paid holidays, including the week between Christmas and New Year’s Day.
• Paid time off and the option to purchase additional vacation time.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level