About this role
AI/ML Engineer1Key Responsibilities
• Build and deploy LLM-based GenAI applications end-to-end • Work with multiple LLMs (OpenAI/Azure OpenAI, Gemini, Claude, LLaMA, Mistral) • Design and implement agentic and multi-agent systems using MCP and A2A • Develop RAG pipelines and document intelligence solutions • Use modern GenAI frameworks (LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, Google ADK, MS CoPilot) • Build AI backend services using FastAPI and Flask • Develop and integrate chat UIs, copilots, and dashboards with AI APIs • Productionize, deploy, and monitor AI systems on cloud platforms • Ensure performance, security, scalability, and Responsible AI compliance Required Skills
• Strong Python programming with FastAPI and Flask • Solid understanding of ML, Deep Learning, NLP, and GenAI concepts • Hands-on experience with LLMs, embeddings, and prompt engineering • Experience designing agentic systems with MCP / A2A • Expertise in RAG architectures and vector databases (FAISS, Pinecone, Weaviate, Chroma, Milvus) • Working knowledge of front-end technologies: HTML, CSS, JavaScript, Stremlit; React preferred • API design and integration (REST / WebSockets) • Strong deployment & MLOps experience: Azure / AWS / GCP, Docker, Kubernetes, CI/CD, MLflow / Azure ML / SageMaker / Vertex AI Good to Have
• Fine-tuning open-source LLMs (LoRA, PEFT, Hugging Face) • Experience with autonomous agents and async workflows • Exposure to RPA + Agentic AI integration • Knowledge of AI governance, monitoring, and security