7 of 7 Retrieval-Augmented Generation Jobs in Colchester

based systems (e.g. LangChain, LlamaIndex, AutoGen, custom agent frameworks) Familiarity with prompt engineering, tool calling, retrieval-augmented generation (RAG), and multi-agent workflows Experience integrating AI into real systems, APIs, event-driven architectures, data pipelines, and automation platforms (e.g. UiPath, Blue Prism) Comfortable experimenting ...

fine-tune LLM-based applications (chatbots, summarization, document Q&A, report generation, code assistants, etc.). Apply prompt engineering, RAG (Retrieval-Augmented Generation), and context-aware pipelines to ensure accuracy and relevance. Integrate AI models with enterprise systems, APIs, and data stores … ethics, security, and governance standards. Prepare and curate training datasets (structured/unstructured text, images, code). Apply data preprocessing, tokenization, and embedding generation techniques. Work with vector databases (Pinecone, Weaviate, FAISS, Chroma) for semantic retrieval use cases. Partner with business stakeholders to identify and shape ...

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 ...

applicants but be currently resident and eligible to work in the UK Demonstrable experience of building and deploying complex AI applications using LLMs, RAG and agentic workflows GraphRAG/Knowledge Graph expertise - deep knowledge with Knowledge Graphs and vector databases Strong technical fluency - TypeScript/React, Langgraph/Langchain, neo4j ...

Transformer-based text classification (BERT/DistilBERT/RoBERTa) • Fine-tuning classification heads • Embeddings + cosine similarity search • Supporting LLM-adjacent work (not deep RAG) Tech Python, sklearn, XGBoost/LightGBM, HuggingFace Transformers, BERT-family models, embeddings, cloud-based ML, CI/CD awareness. What They're Looking For • Strong ...

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 ...

pipelines, and API services Develop sophisticated prompt engineering strategies for LLM-based features, including few-shot learning, chain-of-thought reasoning, and retrieval-augmented generation Optimize models for specific use cases and performance requirements Design and optimize database schemas for relational database Collaborate with ...