AI Support Engineer

Support Engineer, AI Platforms

About the Role

The Support Engineer is the technical frontline for our enterprise AI platform operations. You will own the support queue, resolve platform configuration and integration issues, and maintain service reliability for a user base composed primarily of experienced software developers and senior technical professionals. The expectation is peer-level technical depth: developers will arrive with specific, well-formed problem statements and expect substantive, technically grounded responses. You will work closely with the Team Lead and Adoption Engineer, and interface directly with AI platform vendor support teams on escalations. Scope boundary: This role resolves platform operational and integration issues. Questions about AI model behavior, prompt design, RAG implementation, or AI engineering techniques are out of scope and should be directed to the Engineering team. The boundary is platform operations vs. AI engineering practice. Responsibilities • Own and resolve the AI platform support queue: authentication and SSO failures, IDE and CLI integration issues, proxy and network configuration, API access and rate limit errors, license provisioning problems, and platform-specific behavioral anomalies. • Triage issues accurately distinguish platform configuration problems (this team's scope) from AI model behavior questions or engineering design questions (Engineering team's scope) and route accordingly. • Diagnose and document recurring platform issues; build a knowledge base of root causes, resolution steps, and workarounds that reduces repeat ticket volume over time. • Escalate complex issues to AI platform vendors (Anthropic, Google, OpenAI) with precise reproduction steps, environment details, and diagnostic data; track to resolution.

Support platform administration tasks: license provisioning and deprovisioning, access audits, SSO configuration changes, and policy enforcement in coordination with the Team Lead. • Partner with the Adoption Engineer to distinguish systemic adoption barriers from discrete support issues; feed patterns into platform evaluation and vendor feedback loops. • Participate in incident reviews for platform outages or service degradation events that impact developer productivity. Required Qualifications • 3+ years in a technical support, platform operations, or site reliability role supporting a developer or engineering user base not general IT helpdesk. • Demonstrated ability to troubleshoot at the intersection of: SSO/SAML/OIDC, developer CLI tools and IDE extensions, API authentication and rate limiting, proxy and network configuration, and SaaS platform administration.

Able to read API responses, error logs, and network traces independently; comfortable forming and testing hypotheses without step-by-step escalation guidance. • Clear, technically precise written communication; able to manage a support queue with SLA commitments while maintaining quality of response for a demanding technical audience. • Working familiarity with at least one enterprise AI platform at an operational level sufficient to distinguish a user configuration error from a platform bug. Mandatory Skills • Identity protocols: Hands-on troubleshooting with SAML, OIDC, or OAuth, on at least one identity platform such as Okta, Entra ID / Azure AD, PingFederate, or Google Identity. • Toolchain breadth: Demonstrated troubleshooting in at least two of: IDE extensions (VS Code, JetBrains); CLI tools; REST API authentication, tokens, or rate limits; corporate proxies, VPNs, TLS inspection, or certificate trust; SaaS tenant administration and configuration. • Diagnostics: Ability to work independently with application logs, HTTP status codes (401, 403, 429, 5xx), API response payloads, HAR files, and browser developer tools; familiarity with a log platform such as Splunk, Datadog, or Elasticsearch/Kibana. • Enterprise AI tooling: Operational familiarity with at least one of Anthropic Claude, Google Gemini, or OpenAI ChatGPT Enterprise enough to separate a user configuration error from a platform defect. • Ticketing and SLA: Experience owning a queue in ServiceNow, Jira Service Management, Zendesk, or equivalent, against defined response and resolution targets. • Scripting: Basic scripting in Python, AppScript, Bash, or PowerShell for diagnostics, log parsing, or reproduction of reported issues. Preferred Qualifications • Hands-on experience across multiple enterprise AI platforms Anthropic Claude, Google Gemini, OpenAI ChatGPT Enterprise — at an integration and troubleshooting depth. • Familiarity with enterprise identity platforms (Okta, Azure AD, PingFederate, Google Identity) and their integration with third-party SaaS tools. • Experience supporting developer toolchains: VS Code extensions, JetBrains plugins, GitHub/GitLab integrations, and CI/CD pipeline tooling. • Background supporting large-scale developer environments (1,000+ engineers) where support quality directly impacts engineering velocity