Staff Document Intelligence Engineer

Build document intelligence solutions in Toronto using multimodal models, OCR, semantic retrieval, and production-focused software engineering.This Staff AI Engineer develops systems that extract, interpret, and structure complex documents, including PDFs, tables, drawings, and technical documentation. The position combines Generative AI with vector databases, automated validation, evaluation frameworks, and AWS deployment. It is engineered for production rather than research.Key Responsibilities:
Develop document extraction and interpretation solutionsBuild semantic search using embeddings and vector databasesCombine OCR, multimodal models, and structured outputsDesign benchmark datasets and automated evaluationOptimize inference costs, latency, caching, and scalabilityRequirements:
Seven-plus years of software engineering experienceFive-plus years deploying AI/ML systems into productionExperience with OCR, multimodal LLMs, or document intelligenceExperience with Pinecone, Qdrant, Weaviate, or pgvectorKnowledge of validation, regression testing, and monitoringUse document intelligence, semantic retrieval, and reliable production engineering to advance AI capabilities across Toronto software products.
#J-18808-Ljbffr