Staff Application Engineer

Responsibilities

• Build and operate Databricks data pipelines using bronze, silver, and gold medallion layers with lineage, provenance, access controls, and logging.
• Define domain, ontology, and semantic models in Unity Catalog with subject-matter experts and curate reliable data products.
• Implement data quality tests, monitoring, and alerting for pipelines and products.
• Integrate enterprise systems through APIs, events, and middleware with authentication, retries, reconciliation, and auditability.
• Build production agents and retrieval-augmented applications grounded in governed Databricks data using Unity Catalog functions, Mosaic AI, and model-serving capabilities.
• Implement authorization, approvals, auditability, evaluation sets, and observability for agentic and AI-enabled systems.
• Apply testing, code review, deployment, documentation, on-call support, and architecture decision-making practices.

Requirements

• Bachelor’s degree in a related field or equivalent practical experience.
• 8+ years of experience in data engineering, software or application engineering, or an adjacent enterprise technology role.
• Hands-on experience building production data pipelines with ingestion, semantic or domain modeling, data quality, and lineage.
• Hands-on experience with Databricks, including Unity Catalog, medallion architecture, and Mosaic AI or model serving.
• Experience shipping production retrieval-augmented, conversational, or agentic AI solutions grounded in data pipelines.
• Proficiency in Python and strong software engineering fundamentals, including testing, code review, deployment, and production support.
• Experience integrating enterprise systems through APIs, events, or middleware with authentication, retries, reconciliation, and auditability.
• Experience with an LLM or cloud AI platform such as Vertex AI, Anthropic, or OpenAI and an automation platform such as Workato, n8n, or Camunda.
• Working knowledge of data governance, privacy, and security practices for production data pipelines and products.
• Preferred experience includes the Mosaic AI Agent Framework, Unity Catalog functions, enterprise or federated search, vector databases, permission-aware retrieval, LangGraph, Pydantic AI, LangChain, CrewAI, MLflow tracing, dimensional modeling, master data management, enterprise business-system integrations, GCP or AWS data services, dbt, containers, or serverless computing.

Benefits

• Open paid time off and flexible work schedules.
• Medical, dental, and life insurance.
• Parental leave for employees, spouses or domestic partners, and children.
• 401(k) with company match.