AI Automation Engineer
Salary not listed • Costa Rica • Full-time
Posted 18d ago
About the job
Databricks is seeking an AI Automation Engineer to develop advanced IT automations that enhance the employee experience. This role involves building production-ready AI agents and automation services capable of understanding employee requests, accessing enterprise context, interacting with various systems, and safely executing actions. The focus is on reimagining employee interactions with IT through intelligent, contextual, and agentic experiences, leveraging the Databricks platform.
Responsibilities
- Design, deploy, and run AI agents that interpret natural language, gather context, select tools, execute actions, and communicate outcomes.
- Maintain MCP servers for the AI tools portfolio.
- Build agentic workflows that decompose goals, handle failures, and manage human approvals.
- Ground agents in internal knowledge bases such as policies, runbooks, and SOPs.
- Convert high-volume, repetitive IT support interactions into self-service AI automation experiences.
- Instrument AI automations with logging, metrics, and feedback mechanisms.
- Design and implement AI automations with robust security, including identity governance, RBAC, audit trails, and failure handling.
- Create shared automation infrastructure for credential management, event ingestion, scheduling, and state storage.
- Collaborate with IT Support, Employee Experience, Security, IAM, Infrastructure, and Engineering teams to identify and implement automation opportunities.
- Produce high-quality technical documentation for system designs, operational procedures, and architectural decisions.
Requirements
- Proficiency in Python or Go with at least 3 years of experience.
- Experience with Git-based development, automated testing, and CI/CD.
- Strong experience with REST APIs, OAuth2, event-driven integrations, and enterprise system integrations.
- Proven experience shipping production LLM-powered applications or AI agents.
- Experience with agent patterns including tool/function calling, multi-step workflows, context management, RAG, structured outputs, and plan decomposition.
- Understanding of LLM failure modes such as hallucination, incorrect tool use, and prompt injection.
- Experience evaluating and improving AI systems using automated evals, traces, test datasets, or human feedback.
- Ability to translate complex employee friction problems into simple, reliable technical solutions.
- Strong judgment regarding security, privacy, least privilege, and safe automation in enterprise environments.
- Strong collaboration and cross-functional communication skills.
- Experience with automation or integration platforms (e.g., Tines, MuleSoft, Workato).
- Experience with MCP (Model Context Protocol) server development.