11 of 11 Weaviate Jobs in the UK excluding London

Gemini as well as self-hosted LLMs along with MCP integrations Implement Retrieval-Augmented Generation (RAG) techniques leveraging vector databases (Pinecone/ChromaDB/Weaviate/pgvector/etc), search engines such as ElasticSearch/Solr using both TF/IDF BM25 based full text search as well as similarity ...

MLOps/LLMOps and AI observability Hands-on experience building enterprise RAG solutions using LLMs (e.g. OpenAI, Llama, Mistral, Claude) and vector databases (Pinecone, Weaviate, FAISS, etc.) Practical experience with GenAI frameworks such as LangChain, LlamaIndex, and agentic frameworks like AutoGen, CrewAI, LangGraph Strong Python expertise with AI/ ...

orchestration, memory, evaluation, and observability. Pioneer RAG & Multi-Modal Solutions Implement advanced Retrieval-Augmented Generation (RAG) pipelines using vector databases such as Pinecone and Weaviate . Build multi-modal workflows spanning text, voice, and video, with a strong focus on accuracy, explainability, and performance. Design data ingestion and enrichment pipelines ...

Server, Hugging Face Inference Endpoints API Integration: OpenAI, Anthropic, Cohere, Mistral APIs LLM Frameworks: LangChain, LlamaIndex for building LLM-powered applications Vector Databases: FAISS, Weaviate, Pinecone, Qdrant (Nice-to-Have) Retrieval-Augmented Generation (RAG): Experience building hybrid systems combining LLMs with enterprise data MLOps & Infrastructure MLOps: Model versioning, monitoring, logging ...

Gemini . Implement RAG Pipelines Support the design and delivery of Retrieval-Augmented Generation (RAG) solutions using vector databases such as Pinecone or Weaviate . Develop Production-Ready Services Write clean, maintainable code in Python and/or JavaScript , contributing to microservices and APIs that meet performance, security, and reliability ...

LangSmith or similar Solid NLP background (tokenisation, embeddings, transformers, BERT-style models, sentiment analysis) Experience integrating vector databases (e.g. Azure AI Search, OpenSearch, Pinecone, Weaviate) Cloud experience on Azure, AWS or GCP Familiarity with MLflow, model evaluation frameworks, observability & monitoring Strong understanding of deploying AI systems into real-world production ...

orchestration workflows Designing and maintaining backend services and APIs (primarily Python, FastAPI/Flask) Building and scaling data pipelines and search systems using: ElasticSearch, Weaviate, Pinecone, and other vector databases Engineering secure, containerised architectures using Docker and Kubernetes Ensuring high availability, fault tolerance, and performance for mission-critical workloads Providing ...

with LangChain, LangGraph, and Indexify , with a deep understanding of RAG architectures . Expert-level SQL and experience with BigQuery and vector databases (Pinecone, Weaviate, Vertex AI Search). Proven track record in MLOps and deploying ML models at scale. Experience moving LLM-based prototypes into production environments with thousands ...

production Strong Python development skills Hands-on experience with: Prompt engineering and evaluation Retrieval-Augmented Generation (RAG) Embeddings and vector databases (e.g. FAISS, Pinecone, Weaviate, Chroma) Experience building LLM-backed services using FastAPI/Flask or similar Strong understanding of trade-offs around accuracy, latency, cost and scalability Highly Desirable ...

strategies, document schemas, metadata, hybrid/dense retrieval, re-ranking, and grounding. Manage vector/keyword indexes (e.g., Azure AI Search, pgvector, Pinecone/Weaviate). Develop and deploy advanced NLP, information retrieval, and recommendation systems that enhance Chambers and Partners’ research and product offerings, including document understanding, automatic summarisation ...

systems with large language models. Build and maintain applications using LangChain to orchestrate complex AI workflows. Implement and manage vector databases (e.g., FAISS, Pinecone, Weaviate, Milvus) for fast similarity search and retrieval. Develop embedding pipelines for unstructured data using models like Sentence Transformers, OpenAI, or Hugging Face. Collaborate with data … with large language models (GPT, BERT, etc.). Fine-tuning and prompt engineering. Experience with vector similarity search. Knowledge of popular vector DBs: Pinecone, Weaviate, FAISS, Vespa, Milvus. Generating and managing embeddings (using models like SentenceTransformers, OpenAI, Hugging Face). Familiarity with LangChain for building LLM-powered applications. Ability ...