2 of 2 Remote Semantic Search Jobs in the UK

a strong open-source software background to join a fast-growing scale-up. They offer fully remote employment and have a team of engineers dedicated to developing AI-powered search and Retrieval-Augmented Generation (RAG) pipelines within DataStax-based architecture. This role is perfect for someone with expertise in Open-source, API development, fine-tuning LLMs, and integrating AI … have a passion for optimizing LLM performance, we want to hear from you. Key Responsibilities: Develop and maintain scalable RESTful & GraphQL APIs to interact with LLMs and AI-powered search systems. Design and implement Retrieval-Augmented Generation (RAG) pipelines using open-source tools like LangChain, Langflow, and DataStax Vector Search. Fine-tune LLMs (Hugging Face, OpenAI, Cohere, or similar … to improve response quality and domain-specific performance. Optimize embedding models for better semantic search and document retrieval. Integrate AI-driven solutions with vector databases such as DataStax Astra DB, Weaviate, or FAISS. Implement secure API authentication (OAuth2, JWT) and manage access controls. Collaborate with AI/ML, data engineering, and DevOps teams to ensure seamless system integration. More ❯

LLMs for Retrieval-Augmented Generation (RAG), including open-source implementations. Experience with LLM architecture (e.g., Transformer, GANs, VAEs), Fine-tuning PEFT/LoRA, Context embedding, Vector database technologies, and Semantic Search techniques & tools. Familiarity with Azure cloud platform services and distributed computing frameworks (e.g., SparkNLP) is a plus. Knowledge of Agentic workflows and frameworks. Experience extracting data from More ❯