1 to 25 of 39 Permanent Pinecone Jobs in London

ensuring reliable, secure, and 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 ...

Supervised/unsupervised ML and AI observability•Experience in Enterprise-grade RAG-based solutions with LLMs (OpenAI, Hugging Face, LLaMA, etc.) and vector databases (Pinecone, Weaviate, FAISS).•Experience in designing and scaling GenAI chatbots.•Experience in Agentic AI solutions. Good knowledge of Agentic AI frameworks (LangGraph, AutoGen, CrewAI ...

collaborating effectively with technical and non-technical stakeholders.DesirableExperience with workflow automation platforms such as n8n, Power Automate, Dify or similar.Knowledge of vector databases including Pinecone, Weaviate, Chroma, FAISS or Milvus.Experience building Retrieval Augmented Generation (RAG) solutions.Understanding of AI governance, Responsible AI and AI security principles.Exposure to MLOps, model deployment ...

Qualifications Experience working with open-source AI tools and LLM. Background in AI ethics, fairness, compliance, or regulatory frameworks. Familiarity with Salesforce, vector databases (Pinecone, Weaviate, FAISS), graph-based reasoning, or knowledge graphs. Experience in property maintenance, home services, or customer service automation (not required, but a bonus). Location ...

continuous integration and deployment tools such as **GitLab**, **GitHub**, or **Jenkins**.## **Database Management*** Vector Databases: Experience with and (but not limited to) ChromaDB, Pinecone, PGVector, MongoDB , Qdrant etc.* NoSQL: Familiarity with NoSQL databases (e.g., MongoDB preferred).* SQL: Experience working with SQL databases like PostgreSQL.## **Version Control*** Proficient ...

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 ...

ability to explain technical concepts to both technical and non-technical stakeholders. Desirable Experience AI agents and agentic workflows. Vector databases such as Pinecone, Weaviate, or pgvector. Feature stores including Feast or AWS Feature Store. Docker, Kubernetes, or Amazon ECS. Infrastructure as Code using Terraform or CloudFormation. Big data processing ...

when non-AI approaches are more suitable Desirable Experience Advanced LLM techniques, including agents, tool use and agentic workflows Experience with vector databases (e.g. Pinecone, Weaviate, pgvector) Feature store technologies such as Feast or AWS Feature Store Containerisation and orchestration using Docker, Kubernetes or ECS Infrastructure as Code using Terraform ...

knowledge of state of the art for ML Ops, ML infrastructure, including related tools, design patterns, best practices etc.* Experience with vector databases (e.g., Pinecone, FAISS, Milvus, Weaviate) and information retrieval systems and methods.* Familiarity with media content (video, audio) ML pipelines.* Proficiency in Python and common AI/ ...

least one hyperscaler ML platform (SageMaker, Azure ML, or Vertex AI).Generative AI: LLM fine-tuning (LoRA/QLoRA), RAG architecture design, vector databases (Pinecone, Milvus, Weaviate), and agentic frameworks (LangChain, LangGraph, Semantic Kernel).Data pipelines: data lake/lakehouse architectures, ETL/ELT, and data quality/lineage tooling ...

least one hyperscaler ML platform (SageMaker, Azure ML, or Vertex AI).Generative AI: LLM fine-tuning (LoRA/QLoRA), RAG architecture design, vector databases (Pinecone, Milvus, Weaviate), and agentic frameworks (LangChain, LangGraph, Semantic Kernel).Data pipelines: data lake/lakehouse architectures, ETL/ELT, and data quality/lineage tooling ...

dialogue management. Prompt engineering and Retrieval-Augmented Generation (RAG) . Real-time data streaming platforms such as Kafka . Vector databases including Pinecone, Milvus or Qdrant . Model compression and optimisation techniques including INT8/FP4 quantisation, pruning and knowledge distillation . Deploying machine learning models to resource-constrained ...

platforms including GitHub, GitLab, Jenkins, or similar.Familiarity with monitoring and observability tools for AI applications and services.Database TechnologiesExperience with vector databases such as ChromaDB, Pinecone, PGVector, Qdrant, MongoDB, or similar solutions.Familiarity with NoSQL databases.Experience working with SQL databases, particularly PostgreSQL or equivalent.Version ControlStrong experience using Git and modern version control ...

Foundry or Microsoft Agent Framework Knowledge of MCP and A2A protocols for agent and tool interoperability Hands-on work with vector databases like Pinecone, Weaviate, Qdrant or pgvector Familiarity with distributed systems, workflow engines (Temporal, Airflow or Dagster) and event-driven architectures Experience with open-source LLMs or Small Language ...

dialogue management, prompt engineering, and Retrieval-Augmented Generation (RAG). Data Analytics: Familiarity with real-time data streaming (e.g., Kafka) and vector databases (e.g., Pinecone, Milvus, Qdrant). Quantization: Experience with model compression techniques like quantization (INT8/FP4), pruning, and distillation for edge deployment. #J-18808-Ljbffr ...

appropriately and recognising when non-AI approaches are more suitableDesirable ExperienceAdvanced LLM techniques, including agents, tool use and agentic workflowsExperience with vector databases (e.g. Pinecone, Weaviate, pgvector)Feature store technologies such as Feast or AWS Feature StoreContainerisation and orchestration using Docker, Kubernetes or ECSInfrastructure as Code using Terraform or CloudFormationLarge ...

REST/SDK — for use cases such as document extraction, policy summarisation, or intelligent routing. Build or consume vector-search capabilities (e.g., OpenSearch, Pinecone) for retrieval-augmented generation (RAG) patterns. Use AI coding assistants (Claude Code, GitHub Copilot, Cursor, etc.) fluently as part of your daily development workflow to raise ...

lakehouse architectures. Experience with data integration tools/ETL-ELT frameworks (e.g., Informatica, dbt, Talend, Glue, ADF). Working knowledge of vector databases (e.g., Pinecone, FAISS, pgvector) and RAG architectures. Experience with agent frameworks/protocols (e.g., LangChain, LangGraph, AutoGen, MCP) is highly desirable. Proficiency in SQL and at least ...

communication skills with the ability to explain technical concepts to both technical and non-technical stakeholders.Desirable ExperienceAI agents and agentic workflows.Vector databases such as Pinecone, Weaviate, or pgvector.Feature stores including Feast or AWS Feature Store.Docker, Kubernetes, or Amazon ECS.Infrastructure as Code using Terraform or CloudFormation.Big data processing technologies such ...

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 ...

tools/functions callable by AI agents (tool schemas, function calling, structured outputs). Experience with retrieval-augmented generation (RAG) : vector databases (e.g., Pinecone, Weaviate, pgvector), embeddings, and chunking strategies. Working knowledge of prompt engineering and evaluation techniques for agent reliability, safety, and cost control. Familiarity with orchestrating multi-agent ...

practices, ideally in a regulated environment. Preferred qualifications:Background in financial services or another regulated enterprise environment. Experience with vector databases (for example pgvector, Pinecone, Weaviate, or Chroma) and agent or orchestration frameworks (for example LangChain, LlamaIndex, or the Model Context Protocol). Experience with MLOps/LLMOps tooling such ...

securely, and consistently across teams.• Retrieval-Augmented Generation (RAG) & Knowledge Architecture: Expertise architecting RAG and knowledge-grounded systems—chunking strategies, embeddings, vector databases (e.g., Pinecone, Weaviate, Chroma, pgvector, FAISS), hybrid search, reranking, and retrieval evaluation. Familiarity with advanced patterns such as GraphRAG and agentic RAG to maximize factual grounding … Semantic Kernel, CrewAI, AutoGen). Experience with cloud AI platforms (e.g., Amazon Bedrock, Azure OpenAI/AI Foundry, Google Vertex AI), vector databases (e.g., Pinecone, Weaviate, Chroma, pgvector, FAISS), containerization and orchestration (Docker, Kubernetes), and distributed computing is advantageous.• Architecture Design: Ability to design end-to-end Generative and Agentic ...

etc.) critically and effectively as part of their day-to-day workflow.Bonus points for:Experience with retrieval-augmented generation (RAG) and vector databases (pgvector, Pinecone, or similar).Experience designing multi-agent systems and agent orchestration patterns.Familiarity with LLM observability tools (LangSmith, Langfuse, Arize, or similar).Experience working with multiple model ...

with: Agentic frameworks: LangGraph, LangChain, CrewAI, Agentforce or similar Foundation model providers: Claude Code/Codex/Gemini, OpenAI or AWS Bedrock Vector databases: Pinecone, Weaviate, LlamaIndex or pgvector Cloud platforms: AWS Bedrock, GCP Vertex AI or Azure AI Studio CI/CD for AI: version-controlled prompts, automated testing ...