Data Engineer

Booz Allen Hamilton•McLean, VA

About The Position

Design data architectures and build pipelines, knowledge indexes, and retrieval services that ground AI agents in authorized enterprise information. Work with source-system owners and engineering teams to define data contracts, integrate structured and unstructured sources, and maintain permissions, lineage, quality, and freshness. Own the reliability of data and retrieval services while partnering with AI Engineering on application retrieval behavior and response quality. Engineer positions emphasize pipeline, connector, and service implementation; architect positions emphasize architecture and governance decisions. U.S. citizenship is required due to the nature of the work performed at the facility. Applicants selected will be subject to a government investigation and may need to meet eligibility requirements of the U.S. government client. The position requires the ability to obtain and maintain a Public Trust or Suitability/Fitness determination based on client requirements.

Requirements

Experience designing or implementing enterprise data platforms, lakehouse architectures, and integrations for structured and unstructured data.
Experience with SQL and Python, including developing, testing, and operating ETL or ELT pipelines.
Experience defining data models, schemas, data contracts, APIs, and access patterns for downstream applications.
Experience with data governance, source permissions, lineage, quality controls, and monitoring for freshness and availability.
Knowledge of retrieval-augmented generation, embeddings, vector indexes, and semantic or hybrid search.
Ability to troubleshoot ingestion and retrieval failures and assess relevance, latency, scalability, and data quality.
Ability to translate enterprise requirements into architecture decisions, integration standards, and governance patterns.
Ability to implement and maintain ingestion, transformation, indexing, synchronization, and retrieval services.
Ability to obtain and maintain a Public Trust or Suitability/Fitness determination based on client requirements.
Bachelor's degree.
U.S. citizenship is required.

Nice To Haves

Experience with Databricks, Spark, Delta Lake, vector databases, or comparable platforms.
Experience with permission-aware retrieval, metadata enrichment, incremental ingestion, or knowledge engineering.
Experience delivering reusable customer connectors and data services for production AI applications.

Responsibilities

Design or implement enterprise data platforms, lakehouse architectures, and integrations for structured and unstructured data.
Develop, test, and operate ETL or ELT pipelines using SQL and Python.
Define data models, schemas, data contracts, APIs, and access patterns that support downstream applications.
Maintain data governance, source permissions, lineage, quality controls, and monitoring for freshness and availability.
Implement and maintain ingestion, transformation, indexing, synchronization, and retrieval services.
Troubleshoot ingestion and retrieval failures and assess relevance, latency, scalability, and data quality.
Translate enterprise requirements into architecture decisions, integration standards, and governance patterns.
Own the reliability of data and retrieval services and partner with AI Engineering on retrieval behavior and response quality.