2 of 2 LangChain Jobs in East London

Deployment Model Deployment: Flask, FastAPI, MLflow Model Serving: Triton Inference 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 ...

empirical research environment and partnering with Product teams to deliver and scale validated AI products. Agentic Frameworks: Solid understanding of agentic frameworks (e.g.,LangChain,LangGraph,CrewAI) and practical application for task automation or conversational experiences. Behavioural Modelling & AI Expertise: Experiencemodellingand predicting user engagement, building AI-based search engines, recommender systems ...