2 of 2 Retrieval-Augmented Generation Jobs in York

implement LLM-powered features using both SaaS models and locally hosted models Build and evolve Retrieval-Augmented Generation (RAG) pipelines for both structured and unstructured financial and accounting data Leverage HuggingFace, vLLM, prompt engineering, and model orchestration frameworks to deliver advanced AI solutions Implement … software engineer, including senior-level ownership and decision-making Strong experience building AI-driven systems, with particular depth in LLMs and applied ML (e.g. RAG, prompt engineering, model evaluation) Excellent Python skills and experience delivering production backend systems Strong problem-solving, communication, and collaboration skills A mindset oriented towards ownership ...

both the backend and AI-driven systems. What you'll do: Build scalable backend services and APIs Develop production-grade LLM systems (agentic workflows, RAG, evals) Work on data-heavy, real-world problems in a regulated domain Own features end-to-end and influence architecture Tech: Python, Go, or Node.js … Hands-on experience with agentic systems, RAG, LLM workflows, and evaluations (beyond prompting) Cloud infrastructure experience If you want real ownership and to build AI systems that actually ship, apply for more details. ...