Ai Autom

About the Role

Build production-grade AI agents and enterprise automation services to improve employee IT experiences at Databricks by interpreting natural-language requests, retrieving context, invoking tools/APIs, and safely taking actions across systems.

Builds production LLM-driven agents and agentic workflows—heavy on agent patterns, RAG, and observability.

Location: Costa Rica

Posted: 1 days ago

Category: AI/ML & Data

Vibe Markers: 💻 Open Source, 🔥 Hot

Experience Level: Senior

Job Description

Role

Databricks is hiring an AI Automation Engineer to design, deploy, and operate production AI agents and automation infrastructure that support employee IT interactions. The role focuses on building agentic workflows that understand natural-language requests, retrieve enterprise context, invoke tools and APIs, and act safely with appropriate governance and observability.

Key Responsibilities

• Design, deploy, and run AI agents that interpret natural-language requests, gather context, select tools, execute actions, and communicate outcomes.
• Maintain MCP servers across the AI tools portfolio and build agentic workflows that decompose goals, handle failures, pause for human approval, and resume.
• Ground agents in trusted internal knowledge (policies, runbooks, system documentation, SOPs).
• Turn high-volume support consumer/user journeys into self-service AI automation experiences.
• Instrument automations with logs, metrics, and feedback loops; implement audit trails, RBAC, identity governance, and human-in-the-loop approvals.
• Create shared automation infrastructure (credential vaults, event ingestion, scheduling, approval workflows, cache/state stores) for other teams to build on.
• Collaborate cross-functionally with IT Support, Employee Experience, Security, IAM, Infrastructure, and Engineering to move prototypes to production.
• Produce and maintain high-quality technical documentation describing designs, operations, and architectural decisions.

Requirements

• Proficiency in Python.
• 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.
• Experience shipping production LLM-powered applications or AI agents.
• Familiarity 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, prompt injection, excessive permissions, nondeterministic behavior) and experience evaluating/improving AI systems via automated evals, traces, test datasets, or human feedback.
• Strong judgment around security, privacy, least privilege, and safe automation in an enterprise environment.
• Strong collaboration and communication skills and ability to translate ambiguous problems into reliable technical solutions.
• Experience with automation/integration platforms (examples listed: Tines, MuleSoft, Workato) and MCP server development.

Nice to have

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

Benefits

• Posting references comprehensive, region-specific benefits offered by Databricks (details linked in original posting).

Tech Stack

Python, Git, REST APIs, OAuth2, MCP (Model Context Protocol), Databricks, Agent Bricks, OpenAI Agents SDK, LangGraph, LangChain, MLflow, Vector search, Okta, Microsoft Entra ID, Google Workspace, Jira, Slack, Jamf, GitHub, Workday, Tines, MuleSoft, Workato, LLMs

Skills

System Integration, API Design, Event-driven Architecture, Authentication & Identity Management, CI/CD, Automated Testing, Monitoring & Observability, Security & Governance, Human-in-the-loop Design, Technical Documentation, Collaboration, Problem Solving, Agent Design, Prompting & RAG strategies, LLM evaluation