76 to 100 of 304 Retrieval-Augmented Generation Jobs in the UK

Integrate AI/ML components into applications and operational workflows Design and implement Retrieval-Augmented Generation (RAG) solutions Evaluate LLM performance, identify failure modes, and implement mitigation strategies Test, debug, and improve non-deterministic AI systems Balance AI approaches with deterministic or statistical methods … performance Ability to debug complex, non-deterministic behaviours Strong communication skills to explain AI trade-offs and risks Bonus Skills Hands-on experience with RAG architectures and LLM tooling Experience working in regulated or high-assurance environments Familiarity with AI safety, risk, and governance considerations Background in software engineering (Python ...

agents for function classification, malware family identification, behavioral summarization, and IOC extraction. Create scalable pipelines for static and dynamic analysis, YARA generation Integrate AI models with binary analysis frameworks and disassemblers Fine-tune or evaluate models for reverse engineering and malware analysis tasks Build tooling for unpacking, emulation … cybersecurity or reverse engineering workflows Experience with AssemblyLine, ANGR, Capstone, QEMU, or Frida Familiarity with retrieval-augmented generation (RAG), embeddings, and vector search Knowledge of malware clustering and similarity analysis Experience building autonomous or semi-autonomous security agents Understanding of symbolic execution or program ...

Language Models (LLMs) and understanding of trade-offs between performance, cost, and capability. Understanding of Retrieval-Augmented Generation (RAG), agent orchestration, prompt engineering, and tool calling. Familiarity with AI standards such as Model Context Protocol (MCP) and Agent2Agent (A2A). Familiar with AI orchestration ...

trends, governance considerations, and market developments Technical Focus Areas Agentic AI and enterprise LLM applications Retrieval-Augmented Generation (RAG) architectures AI agents and workflow orchestration AI solution architecture and systems integration Azure OpenAI, AWS Bedrock, GCP Vertex AI, or similar platforms Enterprise AI governance ...

visits 4–5 days/month; occasional team gatherings Salary: €120–£170k base + package discussion Tech: Python, JavaScript, Azure, AWS, AI, LLM's, RAG Industry: AI Consultancy The Role We’re looking for talented Principal-level Forward Deployed Engineers to join our customer-facing AI practice. You’ll work … components, and solution standards AI Mastery & Innovation Implement AI solutions leveraging LLMs, foundation models, and retrieval-augmented generation (RAG) systems Design evaluation frameworks addressing bias, hallucination detection, and business impact Explore novel AI applications while integrating traditional ML techniques where appropriate ...

Machine Learning initiatives across multiple business functions Designing, developing and deploying production-grade AI solutions Building and optimising Large Language Model (LLM) applications, RAG architectures and Agentic AI systems Developing speech-to-text, voice AI and accessibility-focused AI solutions Creating intelligent conversational experiences using modern AI frameworks Architecting scalable … commercial experience designing, training, evaluating and deploying Machine Learning models Experience with Generative AI and Large Language Models Building Retrieval Augmented Generation (RAG) platforms Agentic AI and autonomous workflow development NLP, speech recognition and conversational AI solutions Fine-tuning and optimisation of AI models ...

cloud-native technologies Integrating Large Language Models (LLMs) into existing and new applications Designing Retrieval-Augmented Generation (RAG) solutions and intelligent knowledge systems stablishing best practice around AI governance, security and scalability Experience required Strong commercial experience with C# and .NET development Experience designing ...

cloud-native technologies Integrating Large Language Models (LLMs) into existing and new applications Designing Retrieval-Augmented Generation (RAG) solutions and intelligent knowledge systems stablishing best practice around AI governance, security and scalability Experience required Strong commercial experience with C# and .NET development Experience designing ...

experience with cloud platforms (AWS, Azure, GCP) Experience with ML frameworks (PyTorch, TensorFlow, scikit-learn) and Gen AI/Agentic frameworks (LangGraph, LangChain, VectorDBs, RAG) Understanding of responsible AI practices, including guardrails, hallucination mitigation, and output quality management for AI systems Experience designing and scaling low-latency, customer-facing ...

experience with cloud platforms (AWS, Azure, GCP)Experience with ML frameworks (PyTorch, TensorFlow, scikit-learn) and Gen AI/Agentic frameworks (LangGraph, LangChain, VectorDBs, RAG)Understanding of responsible AI practices, including guardrails, hallucination mitigation, and output quality management for AI systems Experience designing and scaling low-latency, customer-facing ...

client stakeholders and communicating their business impact. Experience in providing solutions using Agent Harness, Retrieval-Augmented Generation (RAG), GraphRAG, knowledge graphs, code agents, deep research agents, and chatbots. Familiarity with AI engineering platforms (Azure AI Foundry, AWS Bedrock). Knowledge of agentic frameworks (Claude ...

tooling or scientific computing. Experience with GPU cluster orchestration. Experience with vector embeddings, ideally retrieval-augmented generation (RAG) and multi-modal representations (e.g. CLIP). Experience with model fine-tuning. Experience with Markov chains or (partially-observable) Markov decision processes. Just state the word ...

Design, build, and deploy LLM-powered applications and GenAI solutions Develop and optimise prompt engineering strategies for performance and accuracy Implement RAG (Retrieval-Augmented Generation) pipelines using structured and unstructured data Fine-tune and customise foundation models and LLMs where required. Integrate GenAI solutions … software engineering, data science, or machine learning Proven experience building and deploying LLM/Generative AI applications in production environments Hands-on experience with RAG architectures, embeddings, and vector search Experience working with LLM APIs and frameworks (e.g., OpenAI, Azure OpenAI, Anthropic, Hugging Face) Strong understanding of prompt engineering techniques ...

experience using frameworks such as PyTorch, TensorFlow, LangChain, or similar. * Experience working with LLMs, prompt engineering, vector databases, and retrieval augmented generation (RAG) architectures. * Strong knowledge of cloud platforms including AWS or Azure. * Experience with data engineering and orchestration tools such as Databricks, Airflow ...

solutions using serverless, containerised and Kubernetes-based environments Generative AI and Large Language Model (LLM) deployment and hosting Retrieval Augmented Generation (RAG), vector databases, semantic search and embedding techniques Python development and AI frameworks such as PyTorch, TensorFlow and LangChain MLOps frameworks ...

engineers and architects. The role combines hands-on technical expertise with strong training and facilitation skills. Experience with Agentic AI, Generative AI, LLM, RAG, DAG, ReAct loop, LangChain, Langgraph, OPA, Rego, MCP server and client etc Key Responsibilities: Deliver instructor-led sessions on modernization, cloud, and application refactoring Conduct live ...

skills in English. Preferred Qualifications Work experience in large-scale e-commerce companies or high-traffic consumer-facing platforms. Experience with LLM fine-tuning, RAG architectures, or generative AI applications. Experience building multilingual or cross-market AI systems for European/global audiences. Experience with real-time inference systems, feature ...

production systems, including: Building and deploying LLM-based applications in production environments Designing agentic workflows and multi-step AI systems Implementing RAG (Retrieval-Augmented Generation) pipelines Working with OpenAI or Anthropic APIs Using vector databases and embedding-based search systems Applying prompt engineering techniques ...

implementing end-to-end AI/ML solutions from development through to deployment and monitoring * Building scalable Generative AI and Agentic AI solutions, including RAG pipelines and orchestration frameworks * Implementing MLOps frameworks, governance and best practices * Translating business requirements into cloud-native AI and data architectures across Azure ...

clearance (requires 5 years of continuous UK residency) Desirable Experience Experience with Agentic frameworks such as LangChain, CrewAI, Autogen, or OpenAI Agents Familiarity with RAG pipelines, MCP, and LLM evaluation tools like LangSmith or TruLens Knowledge of software engineering best practices, including Clean Code (SOLID), TDD, and modular architecture Experience ...

tooling) AWS/Azure cloud platforms (including AI services such as Bedrock) Data engineering tools (e.g. AWS Glue or equivalent) NLP, embeddings, vector databases, RAG architectures MLOps tooling for model deployment and monitoring Experience with distributed data systems and APIs Required Skills & Experience Several years' experience in software engineering, data ...

cloud-native development patterns. Solid understanding of security best practices, IAM, secrets management, and artifact governance. Other Qualifications (OQs): Experience with vector databases, RAG pipelines, or multi-agent AI systems. Exposure to DevOps and infrastructure-as-code (Terraform, Helm, CDK). Hands-on understanding of model drift detection, A/ ...

following: You are good at prototyping and experimenting with emerging technologies to assess feasibility and impact. You have knowledge of vector databases, RAG architectures and their integration into enterprise systems You have experience with GenAI development frameworks or orchestration tools such as Semantic Kernel, AutoGen, LangGraph, LangChain, or PromptFlow. ...

focused on developing next-generation agentic AI systems. This is an opportunity to work hands-on with modern AI technologies including LLMs, RAG pipelines, vector databases, and multi-agent workflows while delivering production-grade AI solutions across multiple business domains. What You’ll Do Design and build agentic … well-tested Python code What We’re Looking For 4+ years of experience in Python engineering Hands-on experience with: RAG (Retrieval-Augmented Generation) Agentic workflows Vector databases Experience with LangChain and LangGraph Experience with cloud platforms such as Azure, AWS, or GCP Good ...

Translate business use cases into Copilot scenarios, prompt flows, connectors and agent behaviours, defining secure, scalable solution architectures. Build and maintain AI components (e.g. RAG, classification, recommendation, summarisation) using Python and modern ML/LLM frameworks. Implement end-to-end MLOps pipelines for development, testing, deployment and monitoring of Copilot … learn, pandas, NumPy). Proven experience integrating AI services with enterprise systems via APIs and event-driven architectures. Practical experience with LLMs, prompt engineering, RAG and tools/plugins for agents and copilots. Familiarity with cloud platforms (ideally Azure) and AI services (e.g. Azure OpenAI, Azure Machine Learning, or equivalents ...