Parsing Architect (AI) - SME
Description
Fantom Corporation is a mission-focused organization supporting critical programs across the defense and intelligence community. We partner with our customers to deliver high-impact technical solutions while fostering a culture built on trust, expertise, and long-term career growth.
We are seeking a Parsing Architect (AI) SME to lead the design, scaling strategy, and governance of enterprise document parsing and preprocessing architectures supporting autonomous agents and large language model (LLM) applications.
You will define how large volumes of multi-format, unstructured data are ingested, validated, parsed, and segmented before indexing. Working across data engineering, AI infrastructure, security, and governance teams, you will establish reliable, cost-effective pipelines that preserve context and deliver secure, traceable information for AI retrieval and analysis.
Education: Bachelor’s degree required
Experience: Minimum of 10 years of relevant experience
Key Responsibilities
-
Lead the architecture and implementation of enterprise document parsing and preprocessing systems.
-
Define ingestion, validation, parsing, and segmentation frameworks for large unstructured data repositories.
-
Establish scaling strategies that support resilient, high-throughput processing and cost-efficient operations.
-
Evaluate and integrate layout analysis engines, optical character recognition (OCR), multimodal vision-language models, and specialized document processing APIs.
-
Define semantic schemas, chunking rules, and metadata tagging standards that preserve context across document libraries.
-
Design retrieval infrastructure, including indexing strategies, vector database integrations, hybrid search, and graph-based retrieval-augmented generation (GraphRAG).
-
Establish access controls across document ingestion, processing, indexing, and retrieval.
-
Implement source lineage and traceability from original documents through processed content and retrieval outputs.
-
Design automated detection and filtering of personally identifiable information (PII) and protected health information (PHI).
-
Partner with security, governance, and compliance teams to translate requirements into architecture standards and technical controls.
-
Establish benchmarks for parsing accuracy, context preservation, throughput, reliability, and operating costs.
-
Guide architecture improvements as LLM context windows, retrieval methods, and application requirements evolve.
-
Document architecture decisions, technology evaluations, and implementation standards.
-
Provide technical direction to engineering teams and resolve complex architectural and integration issues.
Required Qualifications
- Bachelor’s degree.
-
Minimum of 10 years of relevant experience in data engineering, enterprise architecture, document processing, AI infrastructure, or related technical disciplines.
-
Experience designing scalable enterprise architectures for large volumes of unstructured and multi-format data.
-
Experience evaluating and integrating document parsing, OCR, layout analysis, and AI-based document processing technologies.
-
Strong understanding of LLM data preparation, including semantic schemas, chunking strategies, metadata enrichment, and context preservation.
-
Experience designing indexing strategies and integrating vector databases, hybrid search, and graph-based retrieval architectures.
-
Experience implementing access controls, data lineage, and sensitive data filtering within enterprise data pipelines.
-
Ability to establish architecture standards and balance accuracy, scalability, reliability, security, and cost.
-
Experience providing technical leadership across data engineering, AI, security, governance, and compliance teams.
-
Strong analytical, technical documentation, and communication skills.
Preferred Qualifications
-
Experience architecting document processing capabilities for autonomous agents and enterprise RAG applications.
-
Experience comparing traditional parsing methods with multimodal and vision-language approaches.
-
Experience establishing reusable parsing frameworks across multiple teams or document repositories.
-
Experience developing automated evaluation frameworks for extraction fidelity and retrieval quality.
-
Experience modernizing large-scale ingestion and preprocessing environments.
-
Experience supporting federal, defense, intelligence, or other highly regulated environments.
Skills
As published by lever
Resume/CV, Full name, Email, Phone, Current location, Current company, LinkedIn URL, Twitter URL, GitHub URL, Portfolio URL, Fantom Corporation
Sign in to read and join the discussion.