Content Pipeline Engineer

NIH-NCBI • Bethesda, MD

4d • Remote

About The Position

The Content Pipeline Engineer designs and implements reusable pipelines that extract, structure, index, and retrieve information from permitting documents, maps, and other unstructured content. The role builds document-processing capabilities across OCR, document parsing, multimodal extraction, metadata enrichment, vector indexing, semantic retrieval, and agentic workflows. Supported materials include PDFs, scanned forms, well files, plats, survey drawings, maps, and legal descriptions, with the goal of making their content available to downstream applications and AI services. This position is remote.

Requirements

• Bachelor's degree in Computer Science, Software Engineering, Data Science, Information Systems, or a related technical field.
• 5+ years of software engineering, data engineering, search, document-processing, or related experience.
• Strong Python development experience and experience building production-grade data or content-processing pipelines.
• Hands-on experience processing PDFs, images, scanned documents, and semi-structured content using OCR and document-extraction technologies.
• Experience with document stores, search engines, or vector databases, including embeddings and semantic retrieval.
• Experience with document parsing, classification, chunking, metadata enrichment, and preservation of source provenance.
• Experience with LLM-enabled or agentic document-processing workflows, including extraction, validation, routing, or exception handling.
• Experience building robust pipelines with automated testing, logging, monitoring, error handling, and quality controls.
• Experience evaluating OCR and extraction quality using measurable criteria and confidence thresholds.
• Strong problem-solving skills for working with complex and inconsistent document formats.

Nice To Haves

• Experience with OpenSearch.
• Experience with AWS document-processing, AI, or machine-learning services.
• Experience with agentic frameworks such as LangChain, LangGraph, or similar orchestration frameworks.
• Experience with multimodal models, vision-language models, or LLM-based document extraction.
• Experience building RAG or enterprise semantic-search solutions.
• Experience with maps, engineering drawings, plats, survey documents, or legal descriptions.
• Experience extracting bearings, distances, coordinates, or other geospatial information from documents.
• Experience working in the U.S. Federal Government space.
• Experience with permitting, environmental, energy, land-management, or regulatory documents.

Responsibilities

• Design and implement reusable ingestion and processing pipelines for PDFs, scanned documents, images, forms, maps, and other unstructured content.
• Implement OCR and multimodal document-processing workflows for standard documents and map-related materials.
• Extract text, tables, metadata, identifiers, and domain-specific attributes from source documents.
• Extract information from plats and survey drawings, including legal descriptions, labels, bearings, distances, and other spatially relevant information.
• Develop document parsing, classification, normalization, chunking, and metadata-enrichment processes.
• Maintain linkage and provenance between extracted information, source documents, originating systems, and related business records.
• Build document and vector indexes using OpenSearch or comparable technologies.
• Implement embeddings, semantic search, and retrieval pipelines.
• Develop APIs and reusable interfaces for downstream applications and AI services to search and retrieve document content.
• Implement agentic workflows for document classification, extraction-strategy selection, validation, exception handling, and quality assurance.
• Establish confidence thresholds and human-review processes for uncertain or ambiguous extractions.
• Work with GIS engineers to connect map and document extraction results with georeferenced and vectorized geometry.
• Work with Data Scientists to create evaluation datasets and measure OCR, extraction, retrieval, and classification quality.
• Build automated testing, monitoring, and observability for document-processing pipelines.
• Optimize processing for accuracy, throughput, repeatability, and cost.

Benefits

• Medical coverage
• Dental coverage
• Vision coverage
• 401k plan with employer contribution
• Paid holidays
• Vacation
• Tuition reimbursement

What This Job Offers

• Job Type: Full-time