Amaze - Cloud Data Engineer

JD; Key Responsibilities Build LLM-based agents for profiling, modeling, quality, and transformation tasks and collaborate with architects on scalability and governance Agentic Orchestration: Develop sophisticated AI agents using LangGraph for complex data tasks like automated profiling, SQL generation, and data quality remediation. System Design: Build and maintain LLM chains and workflows, ensuring high modularity and reusability. Implement RAG (Retrieval-Augmented Generation) patterns. Collaborate with data science, engineering, and business teams to translate use cases into scalable AI solutions Evaluation & Monitoring: Implement frameworks to monitor agent accuracy, latency, and cost, using tools like RAG-evaluation metrics. Required Skills and Experience Strong hands-on experience in Python for data processing, automation, and backend development Experience working with Generative AI models and frameworks (LLMs, prompt engineering, RAG pipelines, model integration) AI Frameworks: Hands-on expertise in LangChain and LangGraph for building stateful, multi-step agentic workflows. Cloud Stack: Proficiency in the Azure or AWS AI portfolio Data Background: Solid understanding of data pipeline orchestration. AI Safety: Knowledge of prompt versioning, guardrails, and evaluating LLM outputs for "hallucination." Good communication skills to interact with stakeholders and present technical concepts clearly Nice to Have Experience with multi-agent frameworks Familiarity with Databricks, PySpark, Azure Data Factory, or AWS services. Experience in deploying AI solutions within highly regulated enterprise