Content Pipeline Engineer
Core
Design and implement reusable pipelines for extracting, structuring, indexing, and retrieving information from permitting documents, maps, and other unstructured content to support downstream AI services.
Role type
Senior IC content pipeline engineer (document processing & search)
Builds
Document-processing pipelines, vector indexes, semantic retrieval systems, and agentic workflows for unstructured content.
Domain
Energy, land management, and regulatory document processing with GIS integration.
Deliverable
production ML models
Required skills
Python, OCR, document parsing, vector databases, embeddings, semantic search, agentic workflows, automated testing, monitoring, GIS integration
Preferred skills
OpenSearch, AWS document/AI services, LangChain/LangGraph, multimodal/vision-language models, RAG, map/survey document extraction, U.S. Federal Government experience
Technologies
OpenSearch, AWS, LangChain, LangGraph
Responsibilities
Design ingestion pipelines for PDFs, scanned documents, and maps; implement OCR and multimodal extraction; build vector indexes and semantic search; develop agentic workflows for classification and validation; establish confidence thresholds and human-review processes; optimize pipeline accuracy, throughput, and cost.
Seniority
Senior, hands-on IC
