Role & responsibilities

Key Responsibilities
•Design and develop end-to-end data workflows using Dataiku DSS, Flow, Python recipes, Prepare recipes, and Scenarios. •Build document ingestion, extraction, preprocessing, chunking, embedding, and indexing pipelines. •Implement LLM-based solutions using Dataiku LLM Mesh, Knowledge Banks, RAG, Agent Hub, and Agent Connect. •Develop AI agents with tool calling, orchestration, prompt engineering, and structured outputs. •Integrate Dataiku with Snowflake, including Cortex, SQL, and Snowpark where required. •Build forecasting solutions using historical data, structured datasets, and information extracted from documents. •Develop Python-based APIs and integrate Dataiku workflows with React/Next.js applications. •Implement data validation, monitoring, versioning, audit trails, and human-in-the-loop review. •Optimize pipelines for performance, scalability, concurrency, and production deployment. •Maintain code through Git/GitHub and prepare technical documentation.



Required Technical Skills •Robust Python and SQL programming skills. •Hands-on experience with Dataiku DSS and its workflow components. •Experience with Dataiku LLM Mesh, Knowledge Banks, and Agentic AI capabilities. •Strong understanding of RAG architecture, embeddings, vector search, and document processing. •Experience with Snowflake and relational databases. •Experience building REST APIs using FastAPI, Flask, or Django. •Understanding of machine learning, forecasting, and data engineering concepts. •Experience with Git, CI/CD, debugging, and production deployments. Preferred candidate profile Ideal Candidate Someone who can independently design and implement Dataiku-based AI solutions, work across data engineering and GenAI workflows, and translate complex business requirements into scalable production-ready applications. Perks and benefits

📌 Ai Ml Engineer (Ahmedabad)
🏢 Lift Life
📍 Ahmedabad