> Markdown version of [/jobs/ext/3996289-data-retrieval-engineer](https://www.wearedevelopers.com/jobs/ext/3996289-data-retrieval-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Data Retrieval Engineer - **Company:** Ford Motor Company - **Location:** Redford Charter Township, MI, United States - **Experience:** Expert - **Salary:** $85,400.0 - $192,900.0 - **Contract:** Permanent contract - **Skills:** Computer-Aided Design, Application Programming Interfaces (APIs), Artificial Intelligence, Data Analysis, Apache HTTP Server, Google App Engines, BigTable, BigQuery, Cloud Computing, Encodings, Data Validation, Data Discovery, Information Engineering, Data Infrastructure, Data Mapping, Data Retrieval, Query Languages, Software Design Documents, Data Flow Control, Graph Database, Identity and Access Management, Python (Programming Language), Message Queuing Telemetry Transport (MQTT), Neo4j, Regression Testing, OPC Unified Architecture, Cloudera, Search Technologies, SPARQL, Systems Integration, TigerGraph, Data Logging, Google Cloud, Cloud Monitoring, Retrieval-Augmented Generation, Large Language Models, Apache Spark, Generative AI, Firebase, Change Data Capture, Indexer, AI Coding Agents, Backend, Agentic-AI, Vertex AI Vector Search, Kubernetes, Information Technology, Apache Flink, Low-code, Enterprise Integration, Apache Kafka, Search Engines, Milvus, Data Management, Machine Learning Operations, Entity Resolution, Model Context Protocol, Terraform - **Published:** October 28, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=f10b32c9db53f729 ## About the Role * Bachelor's degree in a related field, or equivalent practical experience (5-7+ years) * Professional experience building and operating data platforms, data infrastructure, or backend systems in production. * Strong programming skills in at least one systems or data language such as Python, Go, or Rust, with a track record of shipping maintainable, tested code. * Experience building reusable connectors, ingestion frameworks, or self-service source-onboarding capabilities. This includes designing software that non-platform users operate directly to bring their own sources online. * Production experience with graph databases, graph processing frameworks, or graph query languages. Examples include 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, or Vertex AI Vector Search. * Knowledge of indexing approaches such as adjacency indexes, B-trees, LSM trees, inverted indexes, bitmap indexes, or approximate nearest-neighbor indexes. You can explain when each is the right choice and have used profiling and benchmarking to drive measurable performance improvements. * Experience with metadata catalogs, schema registries, lineage, data discovery, or federated data-product platforms. Examples include BigQuery Analytics Hub. * Familiarity with cloud infrastructure, Kubernetes, observability platforms, and infrastructure-as-code. Hands-on experience with Google Cloud Platform, 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 automate specific parts of an engineering workflow, grounded in fundamentals that do not depend on them. You know which tasks AI handles well, and you verify what it produces. Even better, you may have... * Master's degree in Computer Science, Data Engineering, or a related field. * Experience with streaming and change-data-capture pipelines (Pub/Sub, Dataflow, Datastream, Kafka, Flink, or similar) 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 retrieval infrastructure for AI/ML workloads 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 tooling to end users, such as code-generating agents, low-code integration builders, or natural-language-to-pipeline products, including the human review, sandboxing, and guardrails needed to make generated code safe to deploy. * 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. ## Description * Apply AI to automate the right parts of the work: use AI coding assistants and large language models for repetitive, well-specified steps such as scaffolding connectors, profiling sources, proposing schema mappings, and extending test suites, with validation and engineer review in the loop. * Design self-service, AI-driven connector creation: build the product experience, APIs, and agent workflows that let internal customers describe a source, review an AI-generated connector and its tests, and deploy it through governed guardrails. * Build retrieval for AI consumers: design embedding pipelines on Vertex AI, hybrid search across Vertex AI Vector Search and BigQuery, and graph-aware retrieval so that agents, copilots, and retrieval-augmented generation systems get accurate, governed, low-latency context from connected manufacturing data. * Evaluate AI rigorously: set up evaluation harnesses and benchmarks for AI-assisted onboarding and retrieval quality, measure precision, recall, and latency against real workloads, and decide on evidence where automation is trustworthy enough to ship. * Provide technical leadership: set the technical direction for connectivity and retrieval, author design documents, drive rigorous code and design reviews, and hold the team to a high standard for performance and reliability. * Shape the roadmap: partner with data producers, analytics teams, and AI/ML teams to understand their access patterns and turn them into platform priorities. How success is measured... * Connected data is useful: relationships across sources and domains can be identified, navigated, and reused. * Retrieval is fast and predictable: systems meet defined performance targets under realistic, growing workloads. * The full path is optimized: source connection, ingestion, indexing, discovery, and retrieval are treated as one performance and usability problem. * Speed doesn't compromise trust: data quality, security, governance, lineage, and reliability remain integral to the platform. * New sources connect quickly: onboarding is measurable, repeatable, and increasingly automated rather than dependent on custom integrations.