Technical Support Engineer - Performance & Availability (Monday - Friday, 12pm to 9pm)
Core
Resolve critical incidents and optimize performance for Workday's enterprise SaaS platform and autonomous AI agent workflows.
Role type
Senior IC Technical Support Engineer (AI/LLM & Cloud)
Builds
High-availability enterprise HR and Finance workflows powered by autonomous AI agents
Domain
Enterprise SaaS, Generative AI, Cloud Infrastructure
Deliverable
production ML models | product features | dashboards & analysis
Required skills
LLM pipeline troubleshooting, root-cause analysis, cloud diagnostics (AWS/GCP), observability tooling (Grafana/Kibana), SQL, API debugging, Linux/Windows OS troubleshooting
Preferred skills
Explainable AI (XAI) concepts, severe incident escalation management, complex stakeholder communication
Technologies
AWS, GCP, Azure, Kibana, Grafana, Datadog, Prometheus, Python, Bash, SQL, JSON, XML, Jira, ServiceNow, Salesforce
Responsibilities
Triage high-severity (P1) support queues and manage critical outages; Perform root-cause analysis on software defects and LLM execution failures; Debug cloud-hosted ML service pipelines and LLM orchestration layers; Analyze LLM outputs and conversation logs to identify failure modes and improve prompts/workflows; Write complex SQL queries and scripts to validate backend data integrity; Act as primary technical escalation point for customer IT leadership
Seniority
Senior, hands-on IC
