Python- AI Engineer

Key Responsibilities

• Design, develop, and deploy Generative AI solutions for enterprise applications.
• Build Retrieval-Augmented Generation (RAG) pipelines using vector databases.
• Develop AI agents and multi-agent workflows using LangChain, LangGraph, or similar frameworks.
• Integrate LLMs such as Azure OpenAI, OpenAI GPT, Claude, Llama, or Gemini into production applications.
• Create REST APIs and AI services using Python and FastAPI.
• Optimize prompts, model performance, and inference pipelines.
• Work with embeddings, semantic search, document processing, and knowledge retrieval systems.
• Collaborate with cross-functional teams to deliver scalable AI-powered solutions.
• Implement monitoring, evaluation, and continuous improvement for AI applications.

Required Skills

• 5+ years of experience in software development.
• Strong proficiency in Python.

• Hands-on experience with:

• Generative AI and Large Language Models (LLMs)
• Retrieval-Augmented Generation (RAG)
• Prompt Engineering
• LangChain
• LangGraph
• AI Agents / Agentic AI
• FastAPI
• Vector Databases (Pinecone, FAISS, ChromaDB, Weaviate, or Qdrant)

• Azure OpenAI / OpenAI APIs

• Experience with REST APIs and microservices.
• Knowledge of Git, Docker, and CI/CD pipelines.
• Good understanding of cloud platforms such as Microsoft Azure or AWS.

Preferred Skills

• Azure AI Foundry or Azure AI Studio.
• Azure Cognitive Search / AI Search.
• MCP (Model Context Protocol).
• Knowledge Graphs.
• Kubernetes and containerized deployments.
• MLOps experience.
• Exposure to evaluation frameworks and AI observability