AI ML Engineer with python

About the role

We are seeking an experienced AI Engineer to design, develop, deploy, and support enterprise-grade Artificial Intelligence, Machine Learning, Generative AI, and Large Language Model (LLM) solutions. The ideal candidate will have strong hands-on experience with Python, Generative AI, RAG, LLMs, Azure OpenAI, Azure AI Search, vector databases, AI agents, document intelligence, REST APIs, and cloud-native application development. The candidate will work closely with engineering, architecture, data, security, and business teams to build scalable AI solutions that integrate enterprise data and applications.

Responsibilities

• Design, develop, test, deploy, and maintain production-grade AI/ML and Generative AI applications.
• Build LLM-powered applications using Azure OpenAI, OpenAI APIs, or other enterprise AI platforms.
• Design and implement Retrieval-Augmented Generation (RAG) solutions for enterprise knowledge and document search.
• Develop AI-powered document processing, classification, extraction, summarization, and validation pipelines.
• Build intelligent AI agents using LangChain, LangGraph, Semantic Kernel, or similar frameworks.
• Implement agentic workflows including tool calling, orchestration, state management, context engineering, and structured outputs.
• Develop Python-based AI services, APIs, automation frameworks, and reusable components.
• Build and integrate REST APIs, microservices, and enterprise applications.
• Implement semantic, keyword, vector, and hybrid search capabilities.
• Develop embedding pipelines and integrate vector databases such as Pinecone, FAISS, Weaviate, ChromaDB, PostgreSQL/pgvector, or Azure AI Search.
• Perform prompt engineering, prompt evaluation, context optimization, and response-quality improvement.
• Implement document intelligence solutions using OCR, document extraction, classification, and entity recognition.
• Work with structured and unstructured enterprise data.
• Integrate AI solutions with SQL databases, APIs, data platforms, and enterprise applications.
• Develop model evaluation frameworks to measure accuracy, relevance, latency, cost, and reliability.
• Implement AI guardrails, security controls, monitoring, logging, and observability.
• Containerize AI applications using Docker and deploy them using Kubernetes/AKS or similar platforms.
• Participate in CI/CD implementation using Azure DevOps, GitHub Actions, Jenkins, or equivalent technologies.
• Troubleshoot production AI applications and improve performance and scalability.
• Collaborate with architects, developers, data engineers, cybersecurity teams, and business stakeholders.
• Participate in Agile/Scrum ceremonies, sprint planning, code reviews, and technical discussions.
• Create technical documentation covering architecture, implementation, APIs, AI workflows,