Parsing Architect (AI) - Senior

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. Must possess an active Top Secret Clearance Must be willing and able to obtain a polygraph Education: Bachelor’s degree required Experience: Minimum of 8 years of relevant experience Position Summary The Parsing Engineer (AI) builds, optimizes, and maintains document extraction and chunking pipelines that support large language model (LLM) applications, vector databases, and retrieval-augmented generation (RAG) frameworks. This role transforms complex, unstructured documents into clean, Markdown-formatted content while preserving document structure and context. Working with AI researchers, data engineers, and ML platform teams, the engineer improves the quality of extracted data to support accurate embeddings, effective retrieval, and reliable AI responses.

Responsibilities • Develop and maintain text extraction and preprocessing pipelines for PDFs, presentations, web documents, and files containing charts and tables.

• Preserve document structure during extraction, including heading hierarchies, bulleted lists, and relationships between content sections.

• Transform extracted content into clean, consistently formatted Markdown suitable for embedding and downstream AI processing.

• Implement advanced chunking strategies, including parent-child document relationships and sliding-window chunking, to maintain context and improve retrieval.

• Use tools such as Docling and layout-aware open-source libraries to process complex documents.

• Implement multimodal, vision-based methods for extracting tables and interpreting document layouts.

• Write specialized parsing code to extract data embedded in tables while preserving relationships between headers, rows, and values.

• Enrich text chunks with metadata, including source lineage, temporal information, and classification levels, to support precise filtering and hybrid search.

• Integrate parsing outputs with vector databases, LLM applications, and RAG frameworks.

• Benchmark and tune pipelines for extraction quality, retrieval accuracy, embedding effectiveness, and context window utilization.

• Collaborate with AI researchers, data engineers, and ML platform teams to resolve parsing issues and improve pipeline performance.

Required Qualifications • Must possess an active Top Secret Clearance

• Must be willing and able to obtain a polygraph

• Minimum of 8 years of relevant experience in software engineering, data engineering, document processing, AI data pipelines, or related technical disciplines.

• Experience developing document parsing, text extraction, and preprocessing workflows for unstructured data.

• Ability to preserve semantic structure and produce clean, structured Markdown from complex documents.

• Experience implementing chunking strategies that maintain context, including parent-child relationships and sliding windows.

• Experience with document processing tools such as Docling or comparable layout-aware libraries.

• Experience extracting tabular data from complex documents using programmatic and vision-based techniques.

• Understanding of embeddings, vector databases, LLM applications, and RAG workflows.

• Experience applying metadata enrichment to support source traceability, filtering, and hybrid search.

• Ability to evaluate pipeline quality and troubleshoot issues affecting retrieval accuracy and downstream AI responses.

• Strong collaboration and communication skills.

#CJ

Fantom Corp is a Software Development, Agile Cloud, Software Development, Cyber Security (Risk Management, Assessments & Authorization (A&A)), Data, AI Platform (Computer Vision Models), Podcasting Media Services, and IT Services provider. Established in 2015, Fantom Corp serves Federal customers with top-notch Cybersecurity Architects, Data Scientists/Analysts, Software Engineers/Developers, DevSecOps Engineers, Project Managers, Identity, Credential Access Management (ICAM) services , and Cloud-certified practitioners. We excel in delivering emerging technologies such as Artificial Intelligence (AI) and Machine Learning (ML) with a focus on identifying trends, object detection, and classification of structured and unstructured data. Fantom Corp possesses mastery in all aspects of digital audio production. We lead in the ideation and creation of efforts for clients who want to harness the power of podcasting. We guide them in selecting the right show format for their needs and goals. As a Small Business, we possess the innovation, speed and flexibility to meet your requirements. We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.