in building multi-step intelligent systems, and comfortable working across UI, APIs, cloud AI platforms, and observability tools. You'll work with cutting-edge frameworks like LangChain, LangGraph, LangFlow, CrewAI, and others to build advanced prototypes that integrate short-term and long-term memory, RAG pipelines, vector databases, and more. Key Responsibilities: Rapidly build and iterate on LLM- and agent … prototypes for various use cases (chatbots, copilots, A2A task agents, etc.). Implement agentic workflows, multi-step reasoning pipelines, and memory management using frameworks such as LangChain, LangGraph, LangFlow, CrewAI, Autogen etc. Engineer and tune prompts to enhance performance and reliability of generative tasks. Design RAG systems using vector databases (Pinecone, FAISS, Chroma, PosgreSQL etc.) for contextual retrieval. Incorporate semantic More ❯
in building multi-step intelligent systems, and comfortable working across UI, APIs, cloud AI platforms, and observability tools. You'll work with cutting-edge frameworks like LangChain, LangGraph, LangFlow, CrewAI, and others to build advanced prototypes that integrate short-term and long-term memory, RAG pipelines, vector databases, and more. Key Responsibilities: Rapidly build and iterate on LLM- and agent … prototypes for various use cases (chatbots, copilots, A2A task agents, etc.). Implement agentic workflows, multi-step reasoning pipelines, and memory management using frameworks such as LangChain, LangGraph, LangFlow, CrewAI, Autogen etc. Engineer and tune prompts to enhance performance and reliability of generative tasks. Design RAG systems using vector databases (Pinecone, FAISS, Chroma, PosgreSQL etc.) for contextual retrieval. Incorporate semantic More ❯
deliver real business value. Key Responsibilities * Design, pre-train, fine-tune, and evaluate domain-specific LLMs (e.g., GPT, LLaMA, Mistral) * Build and orchestrate multi-agent architectures using LangChain, LangGraph, CrewAI, or similar * Develop Retrieval-Augmented Generation (RAG) pipelines and apply advanced prompt engineering * Implement secure, scalable inference services using REST/gRPC or event-driven APIs * Construct and maintain enterprise More ❯
AI services (e.g., OCI Data Science, AI Services, Gen AI Agents) that are secure, scalable and optimized for performance & cost. • Build agentic AI solutions using frameworks such as LangGraph, CrewAI, AutoGen.• Design & lead the development of machine learning AI/ML pipelines and fine-tuning pipelines to adapt foundation LLMs to enterprise-specific datasets• Work with embedding models and OCI More ❯
