5 of 5 Permanent Retrieval-Augmented Generation Jobs in Glasgow

Neo4j) or a strong interest in graph data modeling Familiarity with vector search, embeddings, or retrieval-augmented generation (RAG) patterns Exposure to large language model serving, agentic patterns (tool/function calling, Model Context Protocol), or platforms such as Bedrock or Azure OpenAI Experience ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

agentic AI workflows that automate and streamline complex business processes. Design and apply advanced techniques such as semantic search, retrieval‐augmented generation (RAG), named entity recognition (NER), prompt engineering, and personalization for content extraction, search, question answering, reasoning, and recommendation. Develop ...

learning is essential, with solid NLP and financial knowledge and hands‐on implementation experience. The role focuses on advanced techniques such as semantic search, RAG, NER, prompt engineering, and personalization for content #J-18808-Ljbffr ...

logging, and safe rollout patterns Preferred Qualifications, Capabilities, and Skills Experience developing generative AI applications, AI agents, vector search, and retrieval‐augmented generation patterns Experience building AI agents using frameworks such as LangChain, CrewAI, LangGraph, or similar orchestration platforms Experience operating or integrating serving … platforms such as KServe, Ray Serve, NVIDIA Triton Inference Server, Text Generation Inference (TGI), alongside vLLM/llm‐d Familiarity with Amazon SageMaker JumpStart, SageMaker Endpoints, and Amazon Bedrock for managed model hosting Experience with online LLM quality monitoring (e.g., hallucination, toxicity, drift detection) and tracing via OpenTelemetry ...