5 of 5 Remote/Hybrid Retrieval-Augmented Generation Jobs in Surrey

/Vertex AI, including fine-tuning, vector search, and low-latency inference. Build end-to-end LLM applications, leveraging RAG (Retrieval-Augmented Generation), agentic workflows, and prompt engineering. Implement robust evaluation frameworks to monitor LLM quality, hallucinations, token usage, and content safety. Develop … Looking For Essential 5+ years' experience in machine learning engineering or applied AI roles. Recent, demonstrable experience with LLMs, Generative AI, and/or RAG-based systems. Strong Python skills using frameworks such as PyTorch, TensorFlow, Hugging Face, or Google GenAI. Experience with vector databases and retrieval-based ...

Practical experience with AWS (and ideally Terraform, GitLab CI). Experience with agentic systems or LLM-powered automation (e.g. tool-augmented LLMs, RAG workflows, agents for complex workflows). If this sounds like you, reach ...

solutions that improve operational efficiency, regulatory compliance, and customer trust while leveraging advanced analytics and automation. Your Responsibilities Design, develop, and optimize RAG-based solutions integrating retrieval systems with large language models. Build and maintain applications using LangChain to orchestrate complex AI workflows. Implement and manage vector databases … scalable AI-powered applications. Fine-tune and evaluate large language models for specific use cases and domain adaptation. Optimize retrieval and generation workflows for performance, accuracy, and cost-efficiency. Stay updated on the latest advancements in generative AI, retrieval techniques, and vector search technology. ...

Journey and broader Azure AI-related questions. Designing and delivering custom AI solutions on Azure OpenAI Service and Microsoft Foundry, using patterns like RAG, function calling, tool/agent orchestration, and fine-tuning where appropriate. Implementing MCP-based integrations between AI services and existing application components (web apps, APIs, data … Design and optimize data pipelines that prepare structured and unstructured data for model training and RAG solutions. Implement vector search, embeddings, and retrieval-augmented generation workflows. Fine-tune or customize foundation models for domain-specific use cases. Create automated evaluation and monitoring systems ...

deployment. Deep knowledge of RAG Experience processing high volumens of documentation/text Strong knowledge of NLP and LLMs (transformers, fine-tuning, retrieval-augmented methods, agents). Experience conducting applied research and converting experimental outcomes into production systems. Familiarity with retraining workflows and performance monitoring. Understanding ...