Description
Ford is seeking a hands-on Data Retrieval Engineer to make enterprise data fast to connect, fast to retrieve, and fast to bring online.
The ideal candidate will design and build algorithms, architecture, and platform capabilities that connect data across domains, represent relationships effectively, and deliver data with predictable performance at scale.
Responsibilities:
- Design and build the connectivity layer: develop reusable connectors, ingestion frameworks, and self-service onboarding tooling.
- Model relationships across domains: design graph and relational schemas.
- Engineer retrieval for speed: select and implement indexing strategies.
- Own performance end to end: profile, benchmark, and tune the full path.
- Build the discovery surface: integrate with metadata catalogs.
- Make trust a property of the platform: embed data quality checks.
- Instrument everything: define service-level objectives.
- Operate what you build: deploy on Google Kubernetes Engine.
- Build once, scale everywhere: design for global rollout.
- Apply AI to automate the right parts of the work: use AI coding assistants.
- Design self-service, AI-driven connector creation.
- Build retrieval for AI consumers: design embedding pipelines.
- Evaluate AI rigorously: set up evaluation harnesses.
- Provide technical leadership: set the technical direction.
- Shape the roadmap: partner with data producers.
Qualifications:
- Bachelor's degree in a related field or equivalent practical experience.
- Professional experience building and operating data platforms.
- Strong programming skills in at least one systems or data language.
- Experience building reusable connectors.
- Production experience with graph databases.
- Experience with relational and columnar systems.
- Knowledge of indexing approaches.
- Experience with metadata catalogs.
- Familiarity with cloud infrastructure.
- Experience in automotive or manufacturing.