AI Engineer

Durapid Technologies Private Limited; Chennai District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Durapid Technologies Private Limited in Chennai seeks AI Engineer Experts with 6–10 years of experience to drive advanced AI initiatives. You will design, develop, and deploy scalable AI/ML solutions using RAG, agentic systems, and modern LLM frameworks on Azure.

You will build vector database pipelines (Pinecone/Weaviate/Milvus/Azure Search), integrate with backend services, and implement robust CI/CD and testing to ensure reliability and scalability of AI systems.

Qualifications

• 6–10 years of hands-on AI/ML experience.
• Strong experience with RAG and agentic systems.
• Experience with LangChain or LangGraph is a plus.
• Proficient in Azure-based AI deployment and cloud integration.
• Designing vector DB pipelines for fast similarity search.

Responsibilities

• Design, develop, and deploy scalable AI/ML models leveraging RAG and agentic systems.
• Integrate AI models with backend services and Azure cloud infra.
• Design and implement vector database solutions (Pinecone/Weaviate/Milvus/Azure Search).
• Collaborate with product and engineering to define AI use cases.
• Optimize prompts, fine-tuning, and evaluation pipelines for LLM apps.
• Build and maintain agentic AI systems for autonomous tasks.
• Ensure performance, reliability, and CI/CD readiness.
• Stay updated on AI/NLP/MLOps and share knowledge.

Skills

AI/ML

RAG

Agentic systems

Azure

LangChain

LangGraph

Vector databases

SQL/NoSQL

Tools

Pinecone

Weaviate

Milvus

Azure Cognitive Search

Job description

Calling all AI Engineer Experts!

Experience: 6–10 Years

Notice Period: Immediate to 15 Days

Looking for professionals with strong experience in AI | RAG | Agentic | Azure | LangGraph/LangChain | Vector Database |

Role Responsibilities

• Design, develop, and deploy scalable AI/ML models and solutions leveraging RAG, Agentic systems, and modern LLM frameworks (e.g., LangChain, LangGraph).
• Integrate AI models with backend services and cloud infrastructure (preferably on Microsoft Azure).
• Design and implement vector database solutions (e.g., Pinecone, Weaviate, Milvus, Azure Cognitive Search) for efficient similarity search and retrieval.
• Collaborate with product and engineering teams to define AI use cases and translate business requirements into technical implementations.
• Optimize prompt engineering strategies, fine-tuning, and evaluation pipelines for LLM-based applications.
• Build and maintain agentic AI systems that perform autonomous decision-making and task execution.
• Ensure model performance, reliability, and scalability through rigorous testing, monitoring, and CI/CD integration.
• Stay current with the latest advancements in AI, NLP, and MLOps, and contribute to internal knowledge sharing.

Skills: vector,rag,database,langchain,azure