Parsing Architect (AI) - SME
Required skills
- Top Secret Clearance
- polygraph
- data engineering
- enterprise architecture
- document processing
- AI infrastructure
- unstructured data
- multi-format data
- OCR
- layout analysis
Nice to have
- Agile Cloud
- Cyber Security
- Risk Management
- Data
- AI Platform
- Computer Vision Models
Role summary
Fantom Corporation seeks a Parsing Architect (AI) - SME to lead the design, scalability, and governance of enterprise document parsing and preprocessing systems for autonomous agents and LLM applications. This role involves establishing data ingestion, validation, parsing, and segmentation processes, evaluating technologies, and designing cost-effective pipelines. The architect will ensure information is traceable, secure, and accessible, collaborating with data engineering, AI, security, governance, and compliance teams. A Bachelor's degree and minimum 10 years of relevant experience are required, along with an active Top Secret Clearance and willingness to obtain a polygraph.
Education: Bachelor’s degree required
Experience: Minimum of 10 years of relevant experience
Position Summary
The Parsing Architect (AI) leads the design, scalability, and governance of enterprise document parsing and preprocessing systems that support autonomous agents and large language model (LLM) applications. This role establishes how large volumes of unstructured data are ingested, validated, parsed, and segmented for indexing and retrieval.
The architect evaluates document processing technologies and designs reliable, cost-effective pipelines that preserve document context and produce high-quality data for AI applications. The role works closely with data engineering, AI, security, governance, and compliance teams to ensure information remains traceable, secure, and accessible to authorized users.
Responsibilities
Design enterprise architecture for ingesting, validating, parsing, and preprocessing large, multi-format document collections.
Define scaling strategies that support high-throughput processing, reliability, and cost efficiency.
Evaluate and integrate layout analysis engines, optical character recognition (OCR), multimodal vision-language models, and document processing APIs.
Establish semantic data schemas, document segmentation and chunking rules, and metadata 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).
Define and enforce access controls throughout document processing, indexing, and retrieval.
Establish data lineage and traceability from source documents through processed content and retrieval outputs.
Implement automated detection and filtering of personally identifiable information (PII) and protected health information (PHI).
Partner with governance, security, and compliance teams to translate enterprise requirements into architecture standards and technical controls.
Monitor and improve parsing accuracy, contextual completeness, processing performance, and operating costs as AI requirements evolve.
Required Qualifications
