Description

You will design, build, and deploy generative AI solutions on the Azure cloud platform, focusing on LLMs, RAG architectures, and AI agents.

This role is on-site.

Responsibilities

• Develop and maintain AI applications using Python, Azure AI Foundry, and Azure OpenAI services.
• Implement RAG pipelines and orchestrate AI agents using LangChain, Semantic Kernel, and crewAI.
• Manage model lifecycle and deployment workflows via MLOps, Docker, and CI/CD pipelines.
• Build scalable microservices and APIs, integrating with MySQL and Microsoft Fabric for data operations.
• Optimize model performance using TensorFlow, PyTorch, and Scikit-learn within Azure ML environments.

Required Skills

• 8–10 years of experience in AI engineering, with strong proficiency in Python.
• Hands-on experience with Azure AI Foundry, Azure OpenAI, and Azure ML.
• Deep understanding of Generative AI, LLMs, and Retrieval-Augmented Generation (RAG) techniques.
• Practical experience with AI orchestration frameworks: LangChain, Semantic Kernel, and crewAI.
• Proficiency in MLOps practices, containerization (Docker), and CI/CD automation.
• Solid background in machine learning libraries: TensorFlow, PyTorch, and Scikit-learn.
• Experience building APIs and microservices, with database knowledge of MySQL.

Preferred Skills

• Azure AI Engineer Associate or Azure AI Apps & Agents Developer Certification.

Key Skills

Education

Bachelor's degree