Responsibilities :
Design, develop, and deploy enterprise-scale Generative AI solutions using LLMs and foundation models. Build and optimize Retrieval-Augmented Generation (RAG) pipelines for knowledge-based applications. Develop intelligent AI agents and workflows using LangChain, LangGraph, Semantic Kernel, CrewAI, or similar frameworks. Integrate GenAI solutions with enterprise systems, APIs, databases, and third-party services. Implement prompt engineering, prompt tuning, and LLM evaluation frameworks. Deploy, monitor, and scale AI applications on AWS and Azure cloud environments. Design secure and scalable cloud architectures leveraging serverless and containerized services. Implement CI/CD pipelines and MLOps best practices for model deployment and lifecycle management. Collaborate with Data Scientists, ML Engineers, Product Owners, and Architects to deliver business-focused AI solutions. Monitor model performance, latency, cost optimization, hallucination control, and overall system reliability. Stay updated on advancements in LLMs, Agentic AI, Multi-Agent Systems, Vector Databases, and Cloud AI services.
Additional Responsibilities:
Experience with multi-agent frameworks and autonomous AI workflows. Knowledge of Responsible AI, AI Safety, and Governance. Familiarity with model monitoring, evaluation, and feedback loops. Hands-on experience in productionizing GenAI applications. Exposure to distributed systems and microservices architecture.
Technical and Professional Requirements:
GenAI, Generative AI, LLM, RAG, LangChain, LangGraph, Semantic Kernel, Agentic AI, AI Agents, AWS Bedrock, Azure OpenAI, Azure AI Studio, Prompt Engineering, Vector Database, Pinecone, FAISS, ChromaDB, FastAPI, Python, AKS, EKS, Docker, Kubernetes, MLOps, Azure ML, OpenSearch, Hugging Face
