Job Summary

We are looking for an AI / Data Engineer with hands-on experience in Python development, data engineering, and building Retrieval-Augmented Generation (RAG) solutions. The ideal candidate will be responsible for preparing and processing enterprise data for AI applications, developing efficient data pipelines, and implementing retrieval systems using vector databases.

Job Responsibilities

• Design, develop, and maintain data pipelines to support AI and Generative AI applications.
• Build and optimize RAG pipelines, covering data ingestion, preprocessing, chunking, embedding generation, indexing, and retrieval.
• Work with MongoDB and vector databases to store, manage, and retrieve structured and unstructured data.
• Develop data integration and processing solutions to prepare enterprise data for AI applications.
• Implement efficient data retrieval and optimization techniques to improve the accuracy and relevance of AI-generated responses.
• Integrate LLMs and AI applications with enterprise data sources and backend systems.
• Utilize LangChain or similar frameworks to develop and manage RAG workflows.
• Ensure data quality, consistency, scalability, and performance across AI data pipelines.
• Collaborate with AI/ML and software engineering teams to deliver production-ready AI solutions.

Technical Requirements

• Strong Python programming skills.
• Hands-on experience in Data Engineering and building data pipelines.
• Practical experience with MongoDB and vector databases.
• Hands-on experience building RAG pipelines, including:
• Data ingestion and preprocessing.
• Document chunking and embedding generation.
• Vector indexing and similarity search.
• Retrieval optimization and evaluation.
• Experience with data processing, integration, and preparing enterprise data for AI applications.
• Familiarity with LangChain, LlamaIndex, or similar frameworks.
• Understanding of LLMs, embeddings, and semantic search.
• Strong problem-solving and analytical skills.