Description

Design and implement enterprise-grade generative AI solutions across Azure, AWS, or GCP.

This role is hybrid.

Responsibilities

• Architect and deploy LLM-based applications using Azure OpenAI Service and Cognitive Services.
• Develop scalable agentic workflows and RAG pipelines using LangChain, LlamaIndex, and LangGraph.
• Implement advanced prompt engineering strategies for text-to-SQL, summarization, and classification tasks.
• Build and integrate high-performance APIs using FastAPI and manage cloud infrastructure via Azure Functions and Logic Apps.

Required Skills

• 10+ years of software engineering experience with deep expertise in Core Python.
• Proficiency in Azure cloud services, specifically Azure OpenAI Service, Azure Cognitive Services, Azure Functions, and Azure Logic Apps.
• Hands-on experience with hyperscalers AWS and GCP.
• Mastery of LLM techniques, including prompt engineering, RAG, and agentic workflows.
• Strong command of frameworks: LangChain, LlamaIndex, and LangGraph.
• Experience with hosted models like GPT-4, GPT-4-o, or equivalent.
• Ability to write clean, enterprise-grade Python code.

Preferred Skills

• Experience with API development using FastAPI.
• Familiarity with Azure DevOps for CI/CD pipelines.
• Knowledge of SQL for text-to-SQL implementations.

Key Skills

Education

Bachelor's degree