Staff Fullstack Engineer, Agentic Applications

Databricks Databricks · Data AI · Mountain View, CA · Engineering - Pipeline

Staff Fullstack Engineer role focused on architecting and building agentic systems for People Technology workflows at Databricks. The role involves defining agentic platform strategy, integrating enterprise systems as agent tools, and setting technical direction for the pod. Requires strong Python, experience with agentic frameworks, enterprise integration patterns, and data platforms.

What you'd actually do

  1. Architect and build agentic systems that automate and augment People Tech workflows — onboarding, offboarding, comp analysis, policy Q&A, HR service delivery — using LLM orchestration frameworks (LangGraph, AutoGen, or equivalent).
  2. Define the agentic platform strategy for the pod: agent design patterns, tool-calling conventions, retrieval-augmented pipelines, evaluation frameworks, and human-in-the-loop guardrails.
  3. Integrate People Tech systems (Workday, Greenhouse, ADP etc.) as agent-accessible tools and data sources via Databricks Unity Catalog and MCP-style interfaces.
  4. Set the technical bar for the pod — reviewing designs, establishing engineering standards, and leading architectural reviews across the People Tech roadmap.
  5. Influence peers and stakeholders: translate agentic capability into business outcomes for People, Legal, and Finance partners, and mentor engineers in the pod on AI-first thinking.

Skills

Required

  • Python
  • agentic frameworks (LangChain/LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar)
  • enterprise integration patterns
  • REST/GraphQL APIs
  • event-driven architecture
  • connecting SaaS HR/HCM platforms programmatically
  • data platforms (Databricks, Spark, or equivalent)
  • building AI applications on top of lakehouse or warehouse architectures
  • technical lead experience
  • driving architectural decisions
  • writing RFCs
  • raising the quality bar across a team

Nice to have

  • People Tech, HR tech, or internal tooling domains
  • Workday, Greenhouse or similar enterprise HR platforms
  • evaluating and red-teaming LLM agents for safety, reliability, and correctness

What the JD emphasized

  • building production LLM or agentic applications
  • agents, RAG pipelines, tool-use, multi-agent orchestration
  • agentic frameworks
  • building AI applications on top of lakehouse or warehouse architectures
  • technical lead

Other signals

  • architecting and building agentic systems
  • LLM orchestration frameworks
  • agentic platform strategy
  • retrieval-augmented pipelines
  • evaluation frameworks
  • human-in-the-loop guardrails
  • integrating systems as agent-accessible tools
  • building AI applications on top of lakehouse or warehouse architectures