Support Engineer (AI/ML & Platform Operations)

About the Team

At Workday, we bring technical rigor, customer empathy, and a spirit of fun to enterprise software. Our support team underpins operational excellence across Workday's digital experience, AI/ML platform, and Agent Factory initiative. Workday’s Agent Factory is our internal engine that builds, trains, and deploys autonomous AI agents to execute complex HR and Finance workflows, including expense processing, hiring, and workforce scheduling. We partner with core engineering to eliminate bottlenecks, maintain high platform availability, and ensure system reliability for our global customer base.

About the Role

We are seeking a customer-focused Support Engineer to drive incident resolution, root-cause analysis (RCA), and performance optimization across Workday’s enterprise platform and autonomous AI agent workflows. In this high-visibility role, you will analyze system metrics, debug cloud-hosted ML service pipelines, inspect LLM orchestration layers, and manage critical customer escalations within strict SLAs. You will also partner directly with engineering and data science teams through feature iteration and optimization. A key part of this role involves hands-on AI evaluation: analyzing LLM outputs, reviewing conversation logs, and digging into system traces to spot failure modes and translate those insights into prompt, data, and workflow improvements.

Key Responsibilities

Enterprise SaaS & Functional Domain Expertise: Apply operational knowledge of enterprise applications and workflows to validate AI logic and troubleshoot functional processing errors.

Hands-On AI Evaluation: Regularly review LLM outputs, AI conversation logs, and execution traces to identify edge cases, hallucinations, and failure modes. Perform data labeling and translate diagnostic insights into actionable updates for prompts, workflows, and system logic.

Technical Troubleshooting & RCA: Perform root-cause analysis on software defects, performance bottlenecks, and LLM agent execution failures using Kibana, Grafana, and other cloud telemetry tools.

Cloud & LLM Diagnostics: Debug enterprise AI workflows hosted across public cloud environments (AWS, GCP), isolating issues across model hosting services, API gateways, and LLM reasoning pipelines.

Incident & Queue Management: Triage high-severity (P1) support queues, enforce SLAs, and prioritize critical outages over routine inquiries. Participate in weekend on-call rotations for continuous coverage.

Customer Success: Act as the primary technical escalation point for customer IT leadership, clearly explaining root causes, workarounds, and resolution plans during critical incidents.

Database & Code Diagnostics: Write complex SQL queries to validate backend data integrity, debug REST/SOAP API payloads (JSON/XML), and use Python or Bash scripts to automate diagnostics.

Reliability & Product Partnership: Document detailed investigation traces in Jira, ServiceNow, or Salesforce, update runbooks, and partner with engineering and data science teams to deliver permanent fixes and address issue trends.

About You

Basic Qualifications (Required)

Work Experience: Minimum 3 years of experience in technical support engineering, platform operations, or escalation management for enterprise SaaS platforms.

Advanced AI & LLM Systems: Minimum 2 years of hands-on experience reviewing, analyzing, or troubleshooting Large Language Model (LLM) pipelines, prompt/tool-calling structures, or conversation traces/logs.

Cloud & Monitoring Diagnostics:

Minimum 2 years of hands-on experience monitoring, debugging, or troubleshooting services on public cloud infrastructure (AWS, GCP, or Azure).

Minimum 2 years of experience using enterprise monitoring and observability tooling (e.g., Grafana, Kibana, Datadog, or Prometheus).

Technical Stack & Coding:

Minimum 2 years of experience using programming languages or writing and executing SQL queries for data analysis and tuning.

Minimum 2 years of experience analyzing API structures and data serialization formats (JSON or XML).

Minimum 2 years of experience troubleshooting operating systems (Linux or Windows) and cloud networking components.

Operational Availability: Willingness and ability to participate in scheduled weekend on-call coverage rotations

Preferred Qualifications

Bachelor’s degree in Computer Science, Information Technology, Engineering, or a related field (or equivalent practical work experience).

Foundational exposure to Explainable AI (XAI) concepts and model interpretability framework analysis.

Demonstrated history of prioritizing support queues, managing severe incident escalations, and de-escalating critical customer issues.

Strong written and verbal communication skills with the ability to convey complex technical diagnoses to non-technical stakeholders and cross-functional partners.

Pursuant to applicable Fair Chance law, Workday will consider for employment qualified applicants with arrest and conviction records.

Workday is an Equal Opportunity Employer including individuals with disabilities and protected veterans.

Are you being referred to one of our roles? If so, ask your connection at Workday about our Employee Referral process!