1 to 25 of 34 Pinecone Jobs in the UK

Face, LangChain) Oversee integration of LLMs (OpenAI, Anthropic, Gemini, Mistral) via enterprise platforms (Azure OpenAI, Vertex AI) Implement RAG architectures and manage vector databases (Pinecone, Weaviate, FAISS, Milvus) Data & Engineering Excellence Lead the evolution of modern data platforms (Databricks, Snowflake, Synapse, BigQuery) Ensure robust data engineering practices (Airflow, dbt, Prefect ...

Role: Design and build end-to-end Gen AI pipelines using LLMs (Open AI, Azure Open AI, Anthropic) Develop RAG architectures with vector databases (Pinecone, FAISS, Azure AI Search) Optimize LLM outputs using prompt engineering, embeddings, and evaluation techniques Build AI solutions for document processing, compliance, and banking chatbots Develop ...

proficiency in Python , PyTorch/TensorFlow, and GenAI frameworks like LangChain, LlamaIndex, or CrewAI . Data Architecture: Hands-on experience with Vector Databases (e.g., Pinecone, Milvus, Weaviate) and SQL/NoSQL systems. Infrastructure: Proven track record in MLOps , containerization (Docker/K8s), and cloud platforms (Azure/AWS). Ethical ...

Architect Strong expertise in: Generative AI & LLMs, RAG (Retrieval-Augmented Generation), Agentic AI frameworks Hands-on with; LLMs (OpenAI, Llama, Claude, Mistral), Vector DBs (Pinecone, Weaviate, FAISS), Frameworks (LangChain, LlamaIndex, AutoGen, CrewAI, LangGraph) Strong Python + ML frameworks (PyTorch/TensorFlow) Experience deploying on AWS, Azure, or GCP Experience leading ...

working in cloud environments (AWS, Azure, GCP, or Databricks) Familiarity with CI/CD pipelines and modern engineering practices Experience with vector databases (e.g. Pinecone, Chroma) Experience with agent frameworks (e.g. LangChain, LangGraph, or similar) Understanding of AI evaluation frameworks and production readiness Experience working in Agile delivery environments (Agile ...

experience with AI system design, architecture, and distributed systems Expertise in API-based backend development (e.g. FastAPI or similar) Experience with vector databases (e.g. Pinecone, Chroma) Experience with agent frameworks (e.g. LangChain, LangGraph, or similar) Strong understanding of evaluation frameworks for AI/agent systems Experience implementing CI/ ...

technology, digital marketing, or consumer-facing product development. Experience working in embedded consulting or contractor roles within large enterprise environments. Familiarity with vector databases (Pinecone, ChromaDB, Weaviate) and semantic search architectures. Prior experience building and presenting POCs or demo prototypes to senior/executive stakeholders. Experience with multi-agent frameworks ...

Time systems or high-frequency data processing Nice to Have Experience with LLM APIs (eg, OpenAI, open-source LLMs) Knowledge of vector databases (FAISS, Pinecone) Experience with Kubernetes and container orchestration Contributions to open-source or strong GitHub profile ...

embeddings, prompt engineering or fine tuning Exposure to LangChain, LangGraph, Agent Development Kit or similar agent frameworks Experience with vector databases such as Pinecone, Chroma or similar API development experience, ideally with FastAPI or similar frameworks Knowledge of MLOps, LLMOps, CI/CD or production deployment practices Experience designing ...

embeddings, prompt engineering or fine tuning Exposure to LangChain, LangGraph, Agent Development Kit or similar agent frameworks Experience with vector databases such as Pinecone, Chroma or similar API development experience, ideally with FastAPI or similar frameworks Knowledge of MLOps, LLMOps, CI/CD or production deployment practices Experience designing ...

using frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI or similar agent orchestration frameworks Strong experience designing and optimising retrieval systems, including vector stores (Pinecone, Weaviate, Chroma), graph-based RAG architectures, hybrid retrieval, reranking, and semantic search pipelines Experience with production optimisation for RAG systems, including latency optimisation, token cost ...

/indexing, hybrid search, grounding and hallucination mitigation. Applied AI/ML: hands-on with LLMs, embeddings and vector databases (FAISS/Milvus/Pinecone). LLMOps & evaluation: prompt pipelines, automated/offline evaluation, safety/guardrails, telemetry, versioning and CI/CD for ML. Cloud engineering: Azure (preferred ...

architectures. Practical experience working with Claude, OpenAI APIs, and open-source LLMs . Deep understanding of RAG architectures , embeddings, and vector databases (eg Pinecone, Weaviate, OpenSearch, FAISS). Demonstrable experience defining and applying AI governance and responsible AI frameworks . Strong knowledge of LLMOps , CI/CD for models, monitoring ...

pipelines and integrating with enterprise systems (REST, Python, SQL, GraphQL, Webhooks etc). Solid understanding of LLMs, Prompt engineering/tuning, Vector DBs (AstraDB, Pinecone, Weaviate etc), RAG pipelines (LlamaIndex, Haystack) and Agent/Workflow Orchestration (LangChain, LangGraph, CrewAI) Knowledge of SLM Finetuning and Distillation is big advantage. Experience ...

connect multiple services Good communication skills and ability to work with non-technical stakeholders Desired Skills Experience with RAG architectures and vector databases (e.g. Pinecone, FAISS, Azure AI Search) Experience deploying applications on Azure Understanding of CI/CD and software engineering best practices Experience building workflow automation systems Familiarity ...

just experimentation Nice to have: Experience with AWS, Azure, or GCP Experience with LangChain, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar Experience with Pinecone, Weaviate, Qdrant, Chroma, pgvector, or similar Experience with document processing, OCR, structured extraction, or enterprise search Experience in consulting, enterprise delivery, SaaS, or startup environments About ...

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 technical ...

agent-based architectures Comfortable operating in a consulting/client-facing environment Strong communication skills Nice to Have Experience with vector databases (e.g. Pinecone, OpenSearch) Familiarity with LangChain or similar frameworks Broader AWS cloud architecture experience Key Info Rate: £500/day (Inside IR35) Location: Mostly remote Travel: Occasional travel ...

leveraging AI/GAI technologies and large language models (LLMs) Advanced AI Integration : Apply experience with retrieval-augmented generation (RAG), vector databases (e.g. Pinecone, Weaviate, FAISS), and enterprise search for AI-driven knowledge discovery Optimize AI Performance : Utilize practical experience designing structured prompts, fine-tuning models, and cost optimization strategies ...

MongoDB/DynamoDB) Experience with CI/CD, microservices, TDD/BDD. Knowledge of secure system design. Desirable (AI & Data) Vector DBs: Milvus, Weaviate, Pinecone Data orchestration: Airflow, Prefect, Dagster Search: ElasticSearch/OpenSearch AI frameworks: LangChain, Hugging Face MLOps: MLflow, Kubeflow If you are looking for an opportunity ...

regulatory concepts and gap analysis. Maintain high standards for data quality, performance, testing, and engineering practices. Requirements Production experience with vector databases (e.g. Qdrant, Pinecone, Weaviate, pgvector), including tuning for performance and recall Experience building chunking and embedding pipelines for complex documents Strong SQL and data modelling skills in production ...

development and modern software architecture • Understanding of prompt design and managing AI-generated outputs • Ideally have experience in RAG pipelines and vector databases (e.g. Pinecone, Weaviate, pgvector) • Familiarity with cloud platforms is advantageous (AWS, Azure or GCP) • A proactive mindset with the ability to work effectively in a collaborative team ...

queuing (Celery, RabbitMQ, SQS) Event-driven architecture CI/CD pipelines What You'll Work With Python backend services LLM orchestration layers Vector databases (Pinecone, pgvector or similar) API integrations (CRMs, property systems) TypeScript React Next.js Nice to Haves Voice and telephony systems (Twilio, SIP, WebRTC) STT/TTS pipelines ...

architectures (graph‐augmented retrieval for grounded generation); Semantic layer and business intelligence platforms (Looker, dbt Semantic Layer, AtScale); Vector databases and hybrid retrieval (Qdrant, Pinecone, pgvector, AlloyDB vector search); Cloud data platforms at scale (BigQuery, Snowflake, Databricks, Spanner); Data cataloging and governance (Google Knowledge Catalog/Dataplex, Collibra, Alation, Atlan ...

architectures (graph-augmented retrieval for grounded generation)– Semantic layer and business intelligence platforms (Looker, dbt Semantic Layer, AtScale)– Vector databases and hybrid retrieval (Qdrant, Pinecone, pgvector, AlloyDB vector search)– Cloud data platforms at scale (BigQuery, Snowflake, Databricks, Spanner)– Data cataloging and governance (Google Knowledge Catalog/Dataplex, Collibra, Alation, Atlan ...