Active Top-Secret clearance with capability to obtain SCI/CI Poly if needed.
Bachelor's degree in Computer Science, Information Technology, Engineering, or related field (or equivalent experience).
Minimum 8 years of relevant professional experience.
Responsibilities
Build, optimize, and maintain text extraction and chunking pipelines for unstructured data.
Develop workflows that preserve semantic layouts of complex multi-format files.
Transform raw data into clean, markdown-formatted text for improved model accuracy.
Implement advanced parsing strategies at the AI stack's ingestion layer.
Write code to extract data from tables, embedding critical metadata tags.
Collaborate with AI researchers and data engineers to benchmark and tune parsing pipelines.
Benefits
Company-subsidized medical premiums for employees and dependents.
Dental and vision coverage.
401k retirement savings plan with up to 4% match.
Health Savings Account (HSA), FSA, and DCFSA options.
Company-paid short/long-term disability and life insurance.
Generous paid time off and all 11 federal holidays.
Legal and identity protection services.
Bonuses for certifications and reimbursement options.
Employee perks including UberOne, company outings, and discounts on services.
Full Job Description
PID: 26-22-10-015
Summary
E-INFOSOL LLC is seeking a motivated and results-driven Parsing Engineer to join our growing team in Chantilly, VA.
Key Responsibilities
Build, optimize, and maintain the high-fidelity text extraction and chunking pipelines that feed unstructured data into Large Language Model (LLM) ecosystems, vector databases, and Retrieval-Augmented Generation (RAG) frameworks.
Develop extraction workflows that preserve the semantic layout-such as hierarchies, headers, and bulleted lists-of complex multi-format files like PDFs, charts, presentations, and web documents.
Transform raw, chaotic data into clean, markdown-formatted text that maximizes embedding accuracy and minimizes downstream model hallucinations.
Operate at the ingestion layer of the AI stack, implementing advanced parsing strategies-such as parent-child document relationships, sliding-window chunking, and multimodal vision-based table extraction using tools like Docling or layout-aware open-source libraries.
Write specialized code to parse and extract data embedded within tables, infusing each text chunk with critical metadata tags (such as source lineage, temporal data, and classification levels) to enable high-precision hybrid search.
Collaborate closely with AI researchers, data engineers, and ML platform teams and continuously benchmark and tune parsing pipelines to ensure optimal retrieval accuracy and context window utilization.
Required Qualifications
Active Top-Secret clearance with capability to obtain SCI/CI Poly if needed to meet contract requirements.
Bachelor's degree in Computer Science, Information Technology, Engineering, or a related technical discipline (or equivalent experience).
Minimum 8 years of relevant professional experience.
Benefits
Medical - company subsidized premiums for employees, including family and dependent options.
