AI & LLM Solutions Architect

Role overview Lead the design and implementation of generative AI systems, including retrieval-augmented applications, agent workflows, and adapted language models. The work combines hands-on architecture and delivery with evaluation, security, and collaboration with enterprise customers to address challenges involving unstructured data.

Responsibilities - Build scalable retrieval-augmented generation pipelines using frameworks such as LangChain or LlamaIndex and vector stores such as Pinecone or pgvector. - Evaluate, fine-tune, and optimize open-source and proprietary language models for specialized tasks. - Create evaluation approaches and safety guardrails, and improve response latency for interactive systems. - Work with enterprise customers to turn unstructured data needs into practical AI solutions.

Requirements - Deep understanding of transformer models, attention mechanisms, and embedding representations. - Proficiency with Python, PyTorch, FastAPI, and AI development tools such as OpenAI, Anthropic, or Hugging Face SDKs. - Hands-on experience deploying vector search and semantic retrieval at enterprise scale. - Strong grounding in data privacy, enterprise security, and prompt safety.

Benefits and work setup - Equity package, full health and dental coverage, GPU cloud compute allowance, and support for global conferences. - Hybrid or remote work; the role is associated with Oshawa, Ontario.