The AI Agent Data Enablement Engineer is a data engineering role that specializes in building and optimizing embedded Agentic AI solutions using Snowflake and Databricks. The position requires deep expertise in semantic layer modeling, AI governance, LLM cost optimization, and delivering AI‑ready data products in regulated enterprise environments.
Requirements
- 5+ years of experience in data engineering, AI engineering, analytics engineering, or cloud data platform delivery.
- Experience with agentic development practices, including the use of AI agents and coding assistants to accelerate solution design, prototyping, code generation, testing, documentation, deployment preparation, and iterative delivery of data and AI products.
- Hands-on experience with Snowflake and/or Databricks, including data modeling, semantic layer design, data pipelines, performance tuning, and platform optimization.
- Strong knowledge of Snowflake Cortex, including Cortex Analyst, Cortex Search, Cortex Agents, LLM functions, and semantic models.
- Strong knowledge of Databricks Genie and the data modeling, metadata, governance, and Unity Catalog foundations required to enable natural-language analytics.
- Deep understanding of semantic layer modeling, business metrics, KPI definitions, hierarchies, dimensions, governed datasets, and AI-ready data products.
- Experience with data catalogues, metadata management, lineage, data ownership, business glossary, and data quality controls.
- Experience with structured and unstructured data, including enterprise tables, documents, PDFs, SharePoint/Teams content, logs, and business metadata.
- Strong understanding of Snowflake Warehouses and Databricks Clusters / SQL Warehouses, including sizing, workload isolation, autoscaling, performance tuning, and cost optimization.
- Experience with LLM model selection and cost optimization, including model evaluation, token usage, latency, context window, inference cost, and quality/cost trade-offs.
- Ability to assess and optimize LLM usage costs, including token consumption, caching strategies, prompt optimization, model routing, use-case-based model selection, inference cost monitoring, and balancing quality vs. cost.
- Strong SQL and Python skills.
- Practical experience with GenAI, AI agents, RAG, enterprise search, conversational analytics, or LLM-powered assistants.
- Strong knowledge of data governance, RBAC/RLS, masking, auditability, and secure enterprise data access.
- Strong communication skills, with the ability to explain technical decisions to data engineers, architects, product owners, governance teams, and business users.
- Experience in regulated enterprise environments where security, compliance, auditability, and data governance are critical.
Nice to have
- Experience building embedded Streamlit applications, especially on Snowflake or Databricks, to expose AI agents, data products, validation tools, or business-facing workflows.
- Experience with Snowflake Streamlit, Databricks Apps, or similar lightweight application frameworks for data and AI products.
- Experience with cloud-native AI / Agentic AI services, including AWS SageMaker, AWS Bedrock, AWS AgentCore, Azure AI Foundry, Azure OpenAI, Google Vertex AI, or equivalent services for model development, model serving, agent orchestration, knowledge grounding, tool integration, monitoring, and enterprise-scale deployment.
- Experience with agent orchestration frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar.
- Experience with MLOps / LLMOps, including MLflow, model registry, prompt versioning, evaluation pipelines, monitoring, and feedback loops.
- Experience with enterprise integrations such as Power BI, Tableau, Excel, Teams, SharePoint, ServiceNow, Jira, Confluence, CRM platforms, or workflow automation tools.
Additional details
- Role title: AI Agent Data Enablement Engineer
Zobhira
