20 Nov
|
EnableIT
|
Toronto
Lead RAG troubleshooting and LLM evaluation with embeddings, vector search, retrieval optimization, and measurable quality testing.As a Senior Agentic AI Engineer, you will improve how enterprise AI applications retrieve information and generate grounded responses. The role combines RAG pipeline analysis, agentic workflow development, prompt engineering, and quality evaluation. You will work across ingestion, chunking, embeddings, retrieval, reranking, context, and generation.Key Responsibilities:Troubleshoot RAG pipelines from ingestion through response generationOptimize retrieval quality, grounding, relevance, and response accuracyDesign evaluation strategies with metrics and test datasetsImplement prompt engineering, tool calling,
and structured outputsSupport production troubleshooting and continuous application improvementRequirements:Experience developing RAG solutions with embeddings and vector searchExperience evaluating LLM applications with regression testingHands-on agentic AI or LLM application development experienceStrong understanding of context management and multi-step workflowsExcellent communication of technical designs and engineering trade-offsCombine RAG optimization, agentic workflows, and rigorous evaluation to strengthen enterprise LLM application quality and grounding.
📌 Senior Rag And Ai Evaluation Engineer (Toronto)
🏢 EnableIT
📍 Toronto