7 of 7 Semantic Search Jobs in Central London

and high-quality production code, and reviews and debugs code written by others, with a focus on cloud-based systems using AWS and Python. Implements and optimizes RAG-based semantic search and LLM inference workflows using OpenAI and Claude models. Drives decisions that influence the product design, application functionality, and technical operations and processes. Serves as a function … capabilities. Practical cloud-native experience, specifically with AWS. Experience in Computer Science, Computer Engineering, Mathematics, or a related technical field. Preferred qualifications, capabilities, and skills Experience with RAG-based semantic search and LLM inference workflows using OpenAI and Claude models. Proven track record of proposing solutions independently and owning execution end-to-end in an individual contributor role. More ❯

for short-term and long-term agent behaviours. Deploy models and orchestrate AI systems on cloud platforms such as AWS Bedrock, Google Vertex AI, and Azure AI Studio. Integrate semantic search strategies and embeddings to improve LLM relevance and contextual understanding. Build demo-ready user interfaces with tools like Streamlit, Gradio, or React. Develop and maintain robust APIs … credibility with Google - experience working collaboratively with their teams, Google Premier Cloud Partner experience etc Proven track record designing and deploying agentic and generative AI prototypes. Deep understanding of semantic search, vector databases, and memory management strategies. Familiarity with cloud AI tools, observability platforms, and performance optimisation. This is an opportunity to work at the forefront of AI More ❯

for short-term and long-term agent behaviours. • Deploy models and orchestrate AI systems on cloud platforms such as AWS Bedrock, Google Vertex AI, and Azure AI Studio. • Integrate semantic search strategies and embeddings to improve LLM relevance and contextual understanding. • Build demo-ready user interfaces with tools like Streamlit, Gradio, or React. • Develop and maintain robust APIs … credibility with Google - experience working collaboratively with their teams, Google Premier Cloud Partner experience etc • Proven track record designing and deploying agentic and generative AI prototypes. • Deep understanding of semantic search, vector databases, and memory management strategies. • Familiarity with cloud AI tools, observability platforms, and performance optimisation. This is an opportunity to work at the forefront of AI More ❯

for short-term and long-term agent behaviours. • Deploy models and orchestrate AI systems on cloud platforms such as AWS Bedrock, Google Vertex AI, and Azure AI Studio. • Integrate semantic search strategies and embeddings to improve LLM relevance and contextual understanding. • Build demo-ready user interfaces with tools like Streamlit, Gradio, or React. • Develop and maintain robust APIs … credibility with Google - experience working collaboratively with their teams, Google Premier Cloud Partner experience etc • Proven track record designing and deploying agentic and generative AI prototypes. • Deep understanding of semantic search, vector databases, and memory management strategies. • Familiarity with cloud AI tools, observability platforms, and performance optimisation. This is an opportunity to work at the forefront of AI More ❯

with domain-specific knowledge. Prompt engineering and fine-tuning for tailoring model behavior to business-specific contexts. Use of embedding stores and vector databases (e.g., Pinecone, Redis, Azure AI Search) to support semantic search and recommendation systems. Building intelligent features like AI-powered chatbots , assistants , and question-answering systems using LLMs and conversational agents. Awareness of agentic … AI concepts — orchestrating multiple agents with specific tasks/goals in a collaborative, dynamic environment. Familiarity with tools and frameworks that enable LLM-based integrations such as LangChain , Semantic Kernel , or Azure OpenAI . Appreciation for ethical AI considerations including data privacy , security , and bias mitigation . Eagerness to explore emerging technologies and collaborate with AI/ML teams More ❯

AI engineering team. This role is at the cutting edge of applied LLM development—rapidly prototyping intelligent systems that leverage autonomous agents, reasoning workflows, RAG pipelines, and real-time semantic search. You’ll work across frameworks like LangChain, LangGraph, CrewAI, and LangFlow, designing smart, multi-step agents that can interact with APIs, memory modules, structured databases, and UIs. If … and innovate. As a Generative & Agentic AI Engineer, you will: Build fast, iterative prototypes using LLMs and agent frameworks Design and implement agent workflows, memory handling, RAG systems, and semantic search Integrate vector DBs (Pinecone, FAISS, Chroma), cloud AI services, and APIs Develop lightweight UIs (Streamlit, Gradio, React) and observability for demos Work hands-on with prompt engineering … tools Requirements: Strong Python development skills Hands-on experinece working with GCP and Google teams Experience with LangChain, LangGraph, CrewAI, Autogen, or similar frameworks Background in RAG, embeddings, vector search, and memory architecture Familiarity with cloud AI platforms and deploying models via APIs Comfortable building end-to-end prototypes (backend to simple UI) Max 2-month notice period ideally More ❯

CD, Docker, Kubernetes, and AWS Proven delivery of NLP/OCR projects with unstructured data Experience managing or mentoring engineers Bonus points for: Experience in regulated domains Knowledge of semantic search, graph/vector databases Java or C# background and understanding of SOLID principles 📩 Interested? Message me here or email mmatysik@trg-uk.com More ❯