Content Pipeline Engineer
Bethesda, MD
On-site
Job details
- Bethesda, MD
- On-site
- Full-time
- Platform & DevOps
- Posted 26 days ago
Sponsorship history
Past filings by Black Canyon Consulting in public government data. Not a promise of sponsorship.
- Filed 6 H-1B LCAs in FY2025
Full job description
Overview
We are seeking a Content Pipeline Engineer to design and implement reusable pipelines for extracting, structuring, indexing, and retrieving information from permitting documents, maps, and other unstructured content.
The Content Pipeline Engineer will build document-processing capabilities spanning OCR, document parsing, multimodal extraction, metadata enrichment, vector indexing, semantic retrieval, and agentic workflows. The role will support documents such as PDFs, scanned forms, well files, plats, survey drawings, maps, and legal descriptions and make their content available to downstream applications and AI services.
This position is remote.
Duties & 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 both standard documents and map-related materials.
- Extract text, tables, metadata, identifiers, and domain-specific attributes from source documents.
- Support extraction of 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 enabling downstream applications and AI services to search and retrieve document content.
- Implement agentic workflows for activities such as 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.
