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 generation Optimize retrieval quality, grounding, relevance, and response accuracy Design evaluation strategies with metrics and test datasets Implement prompt engineering, tool calling,
and structured outputs Support production troubleshooting and continuous application improvement Requirements:
Experience developing RAG solutions with embeddings and vector search Experience evaluating LLM applications with regression testing Hands-on agentic AI or LLM application development experience Solid understanding of context management and multi-step workflows Excellent communication of technical designs and engineering trade-offs Combine RAG optimization, agentic workflows, and rigorous evaluation to strengthen enterprise LLM application quality and grounding.
#J-18808-Ljbffr
📌 Senior RAG and AI Evaluation Engineer (Winnipeg)
🏢 EnableIT
📍 Winnipeg
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.