1 day ago
Remote, Costa Rica or San José, Costa RicaSenior
Responsibilities
- Resolve incidents, perform root-cause analysis, and optimize performance across Workday’s enterprise platform and autonomous AI agent workflows.
- Review LLM outputs, conversation logs, and execution traces to identify hallucinations, edge cases, and recurring failure modes.
- Perform structured data labeling and communicate findings to senior engineering and data science teams.
- Use Kibana, Grafana, and other monitoring tools to investigate software defects and pipeline execution failures.
- Inspect AI workflows hosted on AWS, GCP, or other public cloud platforms, including model-hosting services and API gateways.
- Monitor and triage support queues, enforce SLAs, handle high-severity incidents, and participate in weekend and holiday on-call rotations.
- Communicate technical updates, workarounds, and resolution steps to customer IT teams.
- Write SQL queries, inspect REST and SOAP API payloads in JSON or XML, and run existing Python or Bash diagnostic scripts.
- Maintain investigation logs in Jira, ServiceNow, or Salesforce and update runbooks and issue-trend documentation.
Requirements
- At least 1 year of experience in technical support, platform operations, or application support for enterprise SaaS environments.
- At least 1 year of experience writing and executing intermediate SQL queries and running diagnostic scripts.
- At least 1 year of experience inspecting JSON or XML API payloads and using basic Linux or Windows command-line tools.
- At least 1 year of hands-on experience with public cloud platforms such as AWS, GCP, or Azure.
- At least 1 year of experience using observability tools such as Grafana, Kibana, or Datadog to inspect logs or traces.
- At least 1 year of experience inspecting, reading, or evaluating AI/LLM conversation logs, traces, or prompt outputs.
- At least 1 year of experience performing queue triage and basic troubleshooting through ticketing workflows.
- Willingness and ability to work scheduled weekend and holiday coverage rotations.
- A bachelor’s degree in Computer Science, Information Technology, Engineering, or a related technical field, or equivalent practical work experience, is preferred.
- Preferred experience includes following runbooks, performing guided autonomous troubleshooting, and drafting technical documentation or customer-facing incident updates.
Categories
Site Reliability
About Workday
Workday builds cloud-based enterprise applications for human capital management and financial management, including payroll, time tracking, expenses, planning, and procurement, sold on a subscription basis with professional services. Founded in 2005 and headquartered in Pleasanton, California, it is a public company traded on NASDAQ as WDAY. Organizations worldwide use Workday to unify HR and finance data, automate processes, and apply AI to workforce and financial operations.