Job Description
AI Architect - AI & Automation
Work Location: Remote
Key Responsibilities:
Own the technical roadmap for AI-driven data modeling, documentation generation, data quality rule generation, and transformation code generation.
Design agentic workflow architecture using frameworks such as LangGraph, CrewAI, or AutoGen.
Ensure all AI workflows operate within the client's AI governance and approval framework.
Lead a small delivery team (AI Tech Lead, AI Developer) through discovery, prioritization, and iterative delivery of automation solutions.
Act as the primary technical point of contact with client platform and data engineering stakeholders.
Required Qualifications 10+ years in data engineering or applied AI/ML, including 2+ years leading applied-AI delivery teams.
Proficiency on Databricks Platform Experience designing agentic or multi-step AI workflows (LangGraph, CrewAI, AutoGen, or equivalent).
Experience building LLM-powered applications, including prompt engineering, context engineering, and Retrieval-Augmented Generation (RAG).
Experience integrating large language models into data engineering pipelines within a governed enterprise environment.
Experience with LLM evaluation and human-in-the-loop validation workflows to ensure accuracy and reliability of AI-generated outputs; working knowledge of guardrails and responsible-AI practices.
Experience building reusable, modular GenAI components (e.g., plugins) using structured multi-agent patterns to enable repeatable automation.
Experience deploying, versioning, monitoring, and evaluating LLM solutions in production, including prompt/version management and feedback-loop mechanisms.
Strong understanding of ETL/ELT patterns, schema analysis, source-to-target mapping, data quality, data profiling and data modeling.
Experience in designing reusable framework integration patterns with Databricks Python, PySpark/Declarative pipelines
Understanding of Data Engineering frameworks such as Data Quality, Data Modelling, Metadata Enrichment, Sensitive data handling, STTM, Modular and testable Python or PySpark/Declarative pipeline code generation.
Experience in designing performance and cost optimized data engineering frameworks Client-facing consulting or delivery experience.
Experience leveraging Agentic coding platforms (for example, GitHub Copilot or Claude Code) effectively.
Preferred Qualifications:
Experience with Databricks AI/ML tooling.
Background in data quality automation or catalog/metadata generation.