Key Responsibilities
- Design, develop, and deploy AI-powered applications using Large Language Models (LLMs) and agentic workflows
- Build intelligent chatbots, AI assistants, and workflow automation solutions
- Develop and optimize Retrieval-Augmented Generation (RAG) pipelines with vector databases
- Design and implement AI Agents and Multi-Agent Systems for reasoning and autonomous task execution
- Integrate tool-calling frameworks and Model Context Protocol (MCP) with external APIs and databases
- Evaluate, benchmark, and monitor AI system performance for continuous improvement
Requirements
- Strong proficiency in Python and scalable application development
- Hands-on experience with Generative AI, LLMs, and AI-powered application development
- Experience with frameworks like LangChain, LangGraph, or CrewAI
- Knowledge of vector databases (Pinecone, Qdrant, Weaviate) and REST API development
- Familiarity with Git, Docker, CI/CD, and cloud platforms (AWS/Azure/GCP)