Senior Content Pipeline Engineer – Remote

Black Canyon Consulting; Bethesda (MD); Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Medical benefits

Dental benefits

Vision benefits

401k with employer contribution

Paid holidays

Vacation

Tuition reimbursement

Job summary

Black Canyon Consulting seeks a Content Pipeline Engineer to design reusable ingestion and processing pipelines for unstructured documents, maps, and permitting data. You will implement OCR, multimodal extraction, and vector indexing to support AI services and downstream applications.

You will collaborate with GIS and data science teams to ensure accurate extraction, provenance, and scalable pipelines, emphasizing quality and cost efficiency. Remote work is available.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, Information Systems, or related field.
• 5+ years of software engineering, data engineering, search, document-processing, or related experience.
• Strong Python development experience and building production-grade data pipelines.
• Experience with PDFs, images, OCR, and semi-structured content extraction.
• Experience with document stores, search engines, or vector databases, including embeddings and semantic retrieval.
• Experience with LLM-enabled or agentic document-processing workflows.
• Experience building robust pipelines with testing, logging, monitoring, and error handling.
• Familiarity with OpenSearch, AWS document-processing, and semantical retrieval.

Responsibilities

• Design reusable ingestion and processing pipelines for PDFs, scanned documents, images, forms, maps, and 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.
• Develop document parsing, classification, normalization, chunking, and metadata-enrichment processes.
• Build document and vector indexes using OpenSearch or comparable technologies.
• Implement embeddings, semantic search, and retrieval pipelines.
• Develop APIs enabling downstream applications and AI services to search and retrieve content.
• Establish confidence thresholds and human-review processes for uncertain extractions.

Skills

Python

OCR

Document processing

Vector search

LLM workflows

Data pipelines

Logging & monitoring

Problem solving

Education

Bachelor's degree in Computer Science

Tools

OpenSearch

AWS

LangChain

LangGraph

Vector databases

Job description

Black Canyon Consulting seeks a Content Pipeline Engineer to design reusable ingestion and processing pipelines for unstructured documents, maps, and permitting data. You will implement OCR, multimodal extraction, and vector indexing to support AI services and downstream applications.

You will collaborate with GIS and data science teams to ensure accurate extraction, provenance, and scalable pipelines, emphasizing quality and cost efficiency. Remote work is available.