Customer Engineer at Baseten

📋 Description

• Be the technical front door for post-sales accounts; triage Tier 1/2 issues; lead P0 war rooms.
• Diagnose runtime issues: latency, memory, GPU usage, concurrency, and model lifecycle.
• Debug infra across Kubernetes, networking, observability, and alerting.
• Pull logs and traces; correlate signals in Grafana/Loki/Prometheus to root causes.
• Lead outages, coordinate across Product/SRE/Infra; deliver root cause analyses after P0/P1.
• Proactive account ownership for top enterprise accounts; set up monitoring and alerts; drive QBRs and expansion.
• Coordinate SA to CE handoffs; maintain runbooks and diagnostic best practices; drive end to end projects.

🎯 Requirements

• Deep Kubernetes troubleshooting with pod/resource debugging; Grafana/Loki/Prometheus.
• Infra debugging across container orchestration, networking, service dependencies; production cluster experience.
• Experience managing high-severity incidents; SLAs, war rooms, post incident reviews, exec comms.
• Strong project management with ownership; run multiple complex, multi-stakeholder initiatives.
• Translate recurring technical pain points into roadmap level insights and product improvements.
• Strong communication and executive presence during high visibility situations.

🎁 Benefits

• Meaningful equity
• 100% coverage of medical, dental, and vision for you and dependents
• Generous PTO including Winter Break
• Paid parental leave
• Company-facilitated 401(k)
• Exposure to ML startups and learning opportunities