Content Pipeline Engineer

This is a fully remote position, open to applicants in Maryland.

📋 Description

• Create and deploy reusable pipelines for the ingestion and processing of PDFs, scanned documents, images, forms, maps, and various forms of unstructured content.

• Execute OCR and multimodal workflows for standard documents as well as materials related to maps.

• Extract text, tables, metadata, identifiers, and domain-specific attributes from source documents.

• Obtain information from plats and survey drawings, including legal descriptions, labels, bearings, distances, and other spatially relevant data.

• Develop processes for document parsing, classification, normalization, chunking, and metadata enrichment.

• Ensure linkage and provenance between extracted data, source documents, originating systems, and associated business records.

• Construct document and vector indexes utilizing OpenSearch or similar technologies.

• Implement embeddings, semantic search, and retrieval pipelines.

• Create APIs and reusable interfaces that allow downstream applications and AI services to search and retrieve document content.

• Develop agentic workflows for document classification, selection of extraction strategies, validation, exception handling, and quality assurance.

• Set confidence thresholds and establish human-review processes for uncertain or ambiguous extractions.

• Collaborate with GIS engineers to link map and document extraction results with georeferenced and vectorized geometry.

• Partner with Data Scientists to develop evaluation datasets and assess the quality of OCR, extraction, retrieval, and classification.

• Build automated testing, monitoring, and observability for document-processing pipelines.

• Optimize processing for accuracy, throughput, repeatability, and cost-effectiveness.

⛳️ Requirements

• Bachelor's degree in Computer Science, Software Engineering, Data Science, Information Systems, or a closely related technical area.

• Over 5 years of experience in software engineering, data engineering, search, document processing, or a related field.

• Proficient in Python development with a proven track record of building production-grade data or content processing pipelines.

• Practical experience in processing PDFs, images, scanned documents, and semi-structured content using OCR and document extraction technologies.

• Familiarity with document stores, search engines, or vector databases, including embeddings and semantic retrieval.

• Experience in document parsing, classification, chunking, metadata enrichment, and maintaining source provenance.

• Knowledge of LLM-enabled or agentic document-processing workflows, covering extraction, validation, routing, or exception handling.

• Proven ability to construct robust pipelines with automated testing, logging, monitoring, error handling, and quality controls.

• Experience in evaluating OCR and extraction quality using measurable criteria and confidence thresholds.

• Strong problem-solving capabilities to address complex and inconsistent document formats.

• Familiarity with permitting, environmental, energy, land management, or regulatory documentation.

🏝️ Benefits

• Medical coverage

• Dental coverage

• Vision coverage

• 401k plan with employer contribution

• Paid holidays

• Vacation

• Tuition reimbursement