7 of 7 Retrieval-Augmented Generation Jobs in South London

/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 ...

Developing and optimizing models for image recognition, object detection, and video analytics. NLP: Building sophisticated systems for sentiment analysis, entity extraction, semantic search, and RAG architectures leveraging LLMs. Generative AI: Exploring and implementing cutting-edge GenAI techniques for content creation, data augmentation, and innovative product features. SME Consulting & Mentorship … with Computer Vision tasks (e.g., CNNs, object detection models like YOLO). NLP: Expert practical experience in NLP techniques, including transformer models, embedding generation, and building complex text-based applications. 3. Leadership & Soft Skills Technical Leadership: Proven track record of leading complex data science projects from research ...

technical stakeholders GenAI work You will work with GenAI in ways that are grounded in real use cases and business value: Building RAG systems that improve search, content discovery or productivity rather than existing for their own sake Implementing guardrails so models do not leak PII or generate harmful … Experience with PyTorch or TensorFlow GenAI specific Hands on experience with LLM APIs or open source models such as Llama or Mistral Experience building RAG systems with vector databases such as FAISS, Pinecone or Weaviate Ability to evaluate and improve prompts and retrieval quality using clear metrics Understanding ...

Have Skills: Strong background in application security, cloud security, or security architecture Hands-on experience with securing AI/ML systems, including LLMs, APIs, RAG pipelines, and vector stores Deep familiarity with AI security risks and threat modeling methodologies Working knowledge of modern DevSecOps practices and tools Excellent communication ...

Centre of Excellence within a consultancy or Microsoft Partner environment. Deep expertise in enterprise AI solution design, including generative AI, Azure OpenAI, Copilot Studio, RAG, cognitive services, and data orchestration patterns. Strong background in the Microsoft ecosystem, especially Dynamics 365, Power Platform, and Azure services. Hands‐on experience shaping ...

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 ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing long-running conversation states, tool usage … executor patterns and manage shared memory across agents. Prompt Engineering & Optimization: utilize programmatic approaches to compile and iteratively improve prompts based on evaluation metrics. RAG Optimization: Enhance retrieval signal through hybrid search, re-ranking, and query rewriting, ensuring high context precision and recall. Observability & Evals: Build robust tracing ...