- Chantilly, Virginia, United States
- 10+ years
Responsible for the systemic design, scaling strategy, and governance of an enterprise-level parsing and document preprocessing architecture engineered specifically for autonomous agents and LLM application stacks.
Responsibilities
- Design the end-to-end framework that governs how massive, multi-format unstructured data lakes are ingested, validated, and programmatically segmented before indexing.
- Build resilient, cost-optimized pipelines capable of streaming contextually rich data into high-throughput AI environments.
- Operate across the boundaries of core data engineering and cognitive computing infrastructure and define unified semantic data schemas, chunking rules, and advanced metadata tagging protocols to maintain context across massive documentation libraries.
- Architect the retrieval infrastructure, establishing the indexing strategies, vector database integrations, and high-assurance access controls necessary for highly secure and accurate hybrid search (GraphRAG).
- Partner with data governance, security, and corporate compliance teams and enforce strict lineage tracing and automated PII/PHI filtering, ensuring that the enterprise data fed into evolving LLM context windows remains performant, compliant, and secure.
Requirements
- Bachelor's degree in Computer Science, Information Technology, Engineering, or a related technical discipline (or equivalent experience).