Enterprise RAG architecture and LangChain expertise anchor this Oshawa, Ontario prospect, offered through hybrid or remote work. Support a global client portfolio. This AI and LLM Solutions Architect role focuses on scalable retrieval systems, vector search, and semantic retrieval at enterprise scale. You will use LangChain, LlamaIndex, Pinecone, and pgvector while addressing unstructured data challenges. The position also covers autonomous agent workflows and real-time response performance. Key Responsibilities:
Build scalable pipelines with LangChain and LlamaIndex Deploy Pinecone and pgvector vector databases Translate unstructured data challenges into AI solutions Optimize latency for real-time AI responses Requirements:
Four or more years of experience Hands-on enterprise vector search deployment experience Semantic retrieval pipeline implementation experience Proficiency with Python, PyTorch, and FastAPI Knowledge of privacy, security, and prompt safety Design enterprise retrieval systems using LangChain, vector databases, semantic search, and secure AI architecture practices.