7 of 7 Permanent Faiss Jobs in the UK

consistent operation. Retrieval‐Augmented Generation (RAG) & Knowledge Architecture – expertise in RAG and knowledge‐grounded systems, including chunking, embeddings, vector databases (Pinecone, Weaviate, Chroma, pgvector, FAISS), hybrid search and retrieval evaluation. Familiarity with GraphRAG and agentic RAG. LLMOps, Evaluation & Responsible AI – operationalizing LLM and agentic systems at scale; evaluation harnesses, quality ...

Hugging Face, including agentic and multi‐step workflows. Proven experience designing and implementing Retrieval‐Augmented Generation (RAG) systems, including vector databases (pgvector, Pinecone, Weaviate, FAISS, etc.) and advanced retrieval strategies (hybrid search, re‐ranking, metadata filtering). Strong understanding of prompt engineering, workflow design, and Gen‐AI optimization, balancing latency ...

LLMs and Generative AI frameworks.* Hands-on experience with:* LangChain/LangGraph* Semantic Kernel* OpenAI APIs/Azure OpenAI* Hugging Face* Vector Databases (Pinecone, FAISS, ChromaDB, Weaviate, Milvus)* Machine Learning fundamentals.* NLP concepts and transformer architectures.* Model evaluation and observability.* Data preprocessing and feature engineering.## **We are a Disability Confident ...

Retrieval‐Augmented Generation (RAG) & Knowledge Systems : Proven experience designing RAG and knowledge‐grounded systems, including chunking strategies, embeddings, vector databases (Pinecone, Weaviate, Chroma, pgvector, FAISS), hybrid search, reranking, and evaluation of retrieval quality. Familiarity with advanced patterns such as GraphRAG and agentic RAG to reduce hallucination and improve factual grounding. … Cloud AI platforms & model hosting: Amazon Bedrock, Azure OpenAI/AI Foundry, Google Vertex AI, Hugging Face Vector databases & retrieval: Pinecone, Weaviate, Chroma, pgvector, FAISS; embeddings, semantic and hybrid search, reranking MLOps/LLMOps & deployment: Docker, Kubernetes, FastAPI, CI/CD; observability, tracing, evaluation tooling (LangSmith, LangFuse); guardrails, prompt/ ...

workflows and autonomous AI systems Knowledge of the Model Context Protocol (MCP) and AI integration patterns Experience with vector databases such as Pinecone, Weaviate, FAISS, or Azure AI Search Experience working with OpenAI and other leading foundation models Knowledge of real-time AI pipelines, including speech-to-text and streaming ...

workloads. Some Other Highly Valued Skills May Include Retrieval Augmented Generation (RAG) and vector database implementation, with practical experience using technologies such as OpenSearch, FAISS or similar to support scalable, production‐ready retrieval workflows. Data pipeline engineering, building and operating AI‐ready pipelines using AWS Glue, S3 and related services ...

latency, cost and output quality. Other Desired Skills Retrieval Augmented Generation (RAG) and vector database implementation, with practical experience using technologies such as OpenSearch, FAISS or similar to support scalable, production-ready retrieval workflows. Data pipeline engineering, building and operating AI-ready pipelines using AWS Glue, S3, and related services ...