Parsing Architect; AI SME

Location: Chantilly, VA
Security Clearance: Active TS or higher [Required]
Job Type: Full-Time
Target Salary Range*:$134,000 - $210,000

* This represents the potential salary range for this position depending on education level, years of experience and/or certifications in addition to other position specific requirements which may impact salary

The Parsing Architect (AI) designs, scales, and governs enterprise parsing and document preprocessing architectures supporting autonomous agents and large language model (LLM) applications. This role establishes frameworks for ingesting, validating, and segmenting large volumes of multiformat, unstructured data before indexing. The architect integrates parsing technologies, semantic schemas, and retrieval infrastructure to deliver context-rich data to AI environments while ensuring performance, cost efficiency, compliance, and security.

• Design enterprise parsing and document preprocessing architectures for autonomous agents and LLM application stacks.
• Establish end-to-end frameworks for ingesting, validating, and programmatically segmenting large, multiformat unstructured data lakes before indexing.
• Define scaling strategies and governance practices for parsing infrastructure.

• Evaluate and orchestrate layout engines, optical character recognition (OCR), multimodal vision-language models, and specialized document processing APIs.
• Build resilient, cost-optimized pipelines that stream context-rich data into high-throughput AI environments.

• Define unified semantic data schemas, chunking rules, and advanced metadata tagging protocols.
• Preserve context across large documentation libraries and data supplied to LLM context windows.

• Architect retrieval infrastructure, including indexing strategies and vector database integrations.
• Establish high-assurance access controls supporting secure, accurate hybrid search and graph-based retrieval-augmented generation (GraphRAG).

• Partner with data governance, security, and corporate compliance teams to enforce data handling requirements.
• Implement strict data lineage tracing and automated filtering of personally identifiable information (PII) and protected health information (PHI).
• Ensure data supplied to LLM applications remains performant, compliant, and secure.

• Minimum of 10 years of experience.

• Enterprise parsing and document preprocessing architecture, scaling, and governance.
• Ingestion, validation, and segmentation of multiformat unstructured data.
• Layout engines, OCR, multimodal vision-language models, and document processing APIs.
• Resilient, cost-optimized data pipeline design for high-throughput AI environments.
• Semantic data schemas, chunking strategies, and metadata tagging.
• Retrieval infrastructure, indexing strategies, vector database integration, and GraphRAG.
• High-assurance access controls, data lineage tracing, and automated PII/PHI filtering.
• Collaboration across data governance, security, and compliance teams.