Remote Content Pipeline Engineer (OCR & AI)

Black Canyon Consulting; United States; À distance; USD 120 000 - 170 000; Plein temps

Résumé du poste

Black Canyon Consulting seeks a Content Pipeline Engineer to design reusable ingestion and processing pipelines for permits, maps, and other unstructured content. You will build OCR, parsing, multimodal extraction, and vector indexing to support downstream AI services.

The role emphasizes embedding workflows, provenance, and robust testing, with a fully remote setup in the United States and collaboration with GIS and data science teams.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, or a related technical field.
• 5+ years of software/data engineering, search, or related experience.
• Experience with PDFs/images and OCR document extraction.
• Experience with vector stores, embeddings, and semantic retrieval.
• Experience with agentic/workflow orchestration frameworks.
• Experience building production-grade pipelines with tests and monitoring.

Responsabilités

• Design reusable ingestion and processing pipelines for PDFs, images, and maps.
• Implement OCR and multimodal document-processing workflows.
• Extract text, tables, metadata, and identifiers from documents.
• Develop parsing, classification, and metadata enrichment.
• Build APIs and interfaces for downstream AI services to query content.
• Establish provenance and linkage between sources and extracted data.
• Set up testing, logging, and monitoring for pipelines.
• Collaborate with GIS and Data Scientists on evaluation datasets.

Connaissances

Python development

Production-grade data pipelines

OCR / document extraction

Multimodal document processing

LLM-enabled workflows

Testing, logging, monitoring

Problem solving with complex formats

Formation

Bachelor's degree in Computer Science or related field

Outils

OpenSearch

LangChain

LangGraph

AWS

Vector databases

Description du poste

Black Canyon Consulting seeks a Content Pipeline Engineer to design reusable ingestion and processing pipelines for permits, maps, and other unstructured content. You will build OCR, parsing, multimodal extraction, and vector indexing to support downstream AI services.

The role emphasizes embedding workflows, provenance, and robust testing, with a fully remote setup in the United States and collaboration with GIS and data science teams.