Source description
About the role
Job Summary We are looking for an experienced AI / Data Engineer to design and build scalable data pipelines and AI-powered applications. The ideal candidate will combine strong data engineering fundamentals with hands-on experience in LLM frameworks, Retrieval-Augmented Generation (RAG), and API development to deliver production-grade AI and data solutions. Key Responsibilities : - Design, develop, and optimize scalable data pipelines using Azure/AWS/GCP Databricks and PySpark. - Develop AI-powered applications using LLMs, LangChain, and LlamaIndex. - Design and implement RAG (Retrieval-Augmented Generation) solutions using enterprise knowledge bases. - Develop REST APIs using Python (FastAPI/Flask) for AI and data services. - Collaborate with Data Scientists, ML Engineers, and Business stakeholders to deliver AI-driven solutions. - Optimize model performance, prompt engineering, and inference pipelines. - Follow DevOps and MLOps best practices for deployment, monitoring, and maintenance. Required Skills & Qualifications : - 3+ years of experience in data engineering, with strong expertise in AWS/Azure/GCP Databricks and PySpark/Python. - Proven experience building and maintaining ETL/ELT pipelines at scale. - Hands-on experience with LLM frameworks such as LangChain and LlamaIndex. - Practical knowledge of RAG architecture and enterprise knowledge base integration. - Solid Python skills, including API development using FastAPI or Flask. - Familiarity with prompt engineering and inference pipeline optimization. - Understanding of DevOps/MLOps practices (CI/CD, model deployment, monitoring). - Strong communication and collaboration skills to work across cross-functional teams. .
More at Durapid Technologies