Description

Own the development and technical leadership of Generative AI solutions, including RAG pipelines, LLM applications, and Copilot extensions.

This role is on-site.

Responsibilities

• Build and enhance Generative AI solutions using Azure OpenAI, Cognitive Search, and Azure ML.
• Develop RAG pipelines involving chunking, embeddings, vector indexing, and retrieval logic.
• Implement LLM-based applications using LangChain and Semantic Kernel.
• Mentor engineering teams, conduct code reviews, and guide implementation best practices.
• Establish evaluation frameworks (RAGAS, DeepEval) and processes for testing LLM outputs.

Required Skills

• 7+ years of software engineering experience, including 2–3 years in AI/LLM projects.
• Hands-on experience with Azure OpenAI, Cognitive Search, and Azure ML services.
• Strong proficiency in Python, FastAPI, React, and TypeScript.
• Experience with LLMs, RAG pipelines, embeddings, vector databases, and prompt engineering.
• Familiarity with LangChain, Semantic Kernel, and vector DBs such as Pinecone or Redis Vector.
• Knowledge of Copilot extensibility, including plugins and Graph Connectors.
• Experience handling unstructured and structured data with SQL, MySQL, and Cosmos DB.

Preferred Skills

• Exposure to MLOps on Azure ML and ETL/data preparation for RAG.
• Experience with multimodal AI (Vision, Document Intelligence, Speech).

Key Skills

Education

Bachelor’s degree