Role Overview
We are looking for a highly skilled AI Engineer with strong hands-on experience in Generative AI, Large Language Models (LLMs), Agentic AI, RAG, and Azure AI technologies. The ideal candidate should be a strong Python developer who can design, develop, optimize, and deploy AI-powered applications from concept to production.
Responsibilities
- Design and develop scalable Generative AI and Agentic AI solutions using LLMs and modern AI frameworks.
- Build AI applications using OpenAI APIs, AutoGen, RAG, and MCP.
- Develop intelligent agents and multi-agent workflows for enterprise use cases.
- Design and implement Retrieval-Augmented Generation (RAG) pipelines.
- Integrate AI solutions with Azure AI Services, Azure Cosmos DB, and other Azure services.
- Develop high-quality, maintainable and scalable solutions using Python.
- Take AI applications through the complete development lifecycle including testing, deployment, and monitoring.
- Optimize AI applications for latency, throughput, scalability, and resource utilization.
Requirements
- 4–6 years of experience in AI/Software Engineering.
- Strong hands-on experience with LLMs and Generative AI.
- Proficiency in Python programming and production-grade API development.
- Hands-on experience with Microsoft Azure and Azure OpenAI.
- Practical experience with AutoGen or similar Agentic AI frameworks.
- Experience with RAG and MCP (Model Context Protocol).
- Experience working with Azure Cosmos DB or Graph databases.
- Proven track record of taking applications from development to production.
Skills
- Python
- Azure
- OpenAI
- AutoGen
- RAG
Nice to Have
- Experience with Docker and Kubernetes.
- CI/CD and DevOps practices.
- Experience with vector databases such as Azure AI Search, Pinecone, or Milvus.
- Knowledge of Azure Functions or AKS.