AI Automation Engineer

Databricks · Costa Rica · Infrastructure · listed October 12, 2026

The shape of it

Seniority
Mid level
Experience asked
3+ years
Where
Not stated
Requirements listed
12
Length
727 words

In the posting’s own words

We're hiring an AI Automation Engineer to build the next generation of IT automations to improve the employee experience at Databricks.

What it asks for · 12

  • Proficiency in Python or Go [3yrs].
  • Experience with Git-based development, automated testing, and CI/CD.
  • Strong experience with REST APIs, OAuth2/authentication frameworks, event-driven integrations, and enterprise system integrations.
  • Shipped production LLM-powered applications or AI agents.
  • Experience with agent patterns: tool/function calling, multi-step workflows, context management, RAG, structured outputs, and plan decomposition.
  • Understanding of LLM failure modes: hallucination, incorrect tool use, ambiguous intent, prompt injection, excessive permissions, and non-deterministic behavior.
  • Experience evaluating and improving AI systems using automated evals, traces, test datasets, human feedback, or similar approaches.
  • Ability to translate ambiguous employee friction problems into simple, reliable technical solutions.
  • Strong judgment around security, privacy, least privilege, and safe automation in an enterprise environment.
  • Strong collaboration and communication skills. You will work cross-functionally to plan, design, and implement automation together.
  • Experience with automation or integration platforms (Tines, MuleSoft, Workato, etc.).
  • Experience with MCP (Model Context Protocol) server development.

Also a plus

  • Experience building agents on Databricks (Agent Bricks) or with frameworks such as OpenAI Agents SDK or LangGraph/LangChain.
  • Experience with MLflow tracing/evaluation, vector search, and LLM observability.
  • Experience integrating IT platforms: Okta/Microsoft Entra ID, Google Workspace, Jira, Slack, Jamf, GitHub, Workday, or SaaS administration APIs.
  • Familiarity with identity lifecycle, access management, device management, and software provisioning.

What the job covers

  • Build AI agents and automations: Design, deploy, and run AI agents that support all of our employees. The agents interpret natural-language requests, gather context, select tools, execute actions, and communicate outcomes.
  • Maintain MCP servers across our AI tools portfolio.
  • Build agentic workflows that decompose goals into steps, handle failures, pause for human approval as needed, and resume their workflows.
  • Ground agents in trusted internal knowledge (policies, runbooks, system documentation, SOPs, etc).
  • Turn high-volume support CUJs into self-service experiences: Identify repetitive, high-friction IT interactions and convert them into reliable AI automation experiences.
  • Instrument AI automations with logs, metrics, and feedback loops.
  • Design and implement AI automations with identity governance, tools RBAC, human-in-the-loop approvals where applicable, audit trails, and failure handling.
  • Create shared automation infrastructure (credential vaults, event ingestion, scheduling, approval workflows, cache/state stores) that other teams can build on.
  • Work with IT Support, Employee Experience, Security, IAM, Infrastructure, and Engineering to identify automation opportunities and take solutions from prototype to production.
  • Write and maintain high-quality technical/engineering documentation that clearly communicates system designs, operational procedures, and architectural decisions.

Tools and skills named

Ways of working
  • Technical writing2×
  • Git
  • Jira
  • Slack
  • Testing
Models & research
  • LLM3×
  • Evaluations
Security & compliance
  • Security2×
  • Audit
  • IAM
Data
  • Databricks3×
Cloud & infra
  • CI/CD
  • Observability
Frameworks
  • REST2×
Languages
  • Go
  • Python
Go to market
  • SaaS
Operations & finance
  • SOPs

Words the posting leans on

  • experience14×
  • automation12×
  • agents10×
  • system5×
  • tools5×
  • workflows5×
  • build4×
  • context4×
  • design4×
  • apis3×
  • approval3×
  • enterprise3×
  • failure3×
  • integrations3×
  • management3×
  • support3×

Counted from the posting after the mission statement and the legal notices are set aside. The ones near the top are the ones a screener is looking for.

The posting, your resume, and the gaps between them. One click loads all three.

More open at Databricks

every open role at Databricks →

How this page was made

An automated read of a public job posting, fetched November 2, 2026 and last changed by Databricks on October 16, 2026. Every list above is pulled from the posting’s own sentences — nothing rewritten, nothing added, no judgment about the role or the company. Counts and seniority are read off the text by rule, so they can be wrong where the posting is unusual. The original is the only thing that binds. Openings close without warning; check the source before spending an evening on it.