- Design, develop, and deploy AI agents and end-to-end GenAI solutions to solve complex business and engineering challenges.
- Collaborate with domain experts and stakeholders to understand processes and translate requirements into AI-driven solutions.
- Build and integrate solutions using Azure AI services, including Azure OpenAI, Azure AI Foundry, Azure Machine Learning, AI Search, and Cognitive Services.
- Develop Retrieval-Augmented Generation (RAG) pipelines, AI copilots, chatbots, and agentic workflows leveraging enterprise knowledge sources.
- Implement prompt engineering, tool/function calling, workflow orchestration, and multi-agent frameworks using LangChain, Semantic Kernel, or similar technologies.
- Deploy, monitor, and optimize AI applications in production while ensuring security, governance, scalability, and performance.
- Establish LLMOps/MLOps practices for model deployment, evaluation, monitoring, and continuous improvement.
- Strong programming skills in Python.
- Hands-on experience with Azure AI ecosystem (Azure OpenAI, Azure AI Foundry, Azure ML, AI Search, Cognitive Services).
- Experience building LLM-based applications, AI agents, RAG solutions, and GenAI-powered applications.
- Knowledge of prompt engineering, vector databases, semantic search, and orchestration frameworks (LangChain, Semantic Kernel, AutoGen, etc.).
- Strong analytical, problem-solving, and stakeholder management skills.
- Familiarity with cloud-native development, APIs, and MLOps/LLMOps practices.