Senior Manager of Cloud Platform & Site Reliability

Role overview

Baseten is hiring a Senior Manager, Cloud Platform & Site Reliability (full remote). You will lead and grow the organization responsible for the infrastructure powering Baseten’s machine learning platform—setting technical direction, reliability standards, and scaling the SRE/platform engineering practice alongside product growth.

Key missions

• Lead and grow the infrastructure organization that powers Baseten’s ML platform.
• Set org-level technical direction and roadmap for infrastructure, reliability, and platform engineering.
• Own end-to-end reliability posture for the platform by defining and enforcing standards for:
  • SLOs/SLIs
  • Incident response
  • Observability-as-code
  • Runbooks
  • Post-incident reviews
• Drive cross-functional collaboration and ensure best practices are adopted and maintained across the organization.

Responsibilities

• Own the end-to-end health of cloud infrastructure and the SRE practice.
• Engage credibly in architectural decisions while still setting organization-wide direction.
• Lead incident management, including executive-level communication during high-severity incidents and disciplined post-incident follow-through.
• Lead complex, multi-stakeholder technical initiatives from scoping through execution.
• Manage and grow multiple infrastructure/platform/SRE teams, including managers.

Requirements

• Strong ability to zoom out for org-level strategy while staying technically credible across:
  • Kubernetes and multi-cloud infrastructure
  • Reliability engineering and distributed systems
• Excellent communication with executive presence; can explain technical work to technical and non-technical audiences.
• Experience owning incident management and enterprise SLAs at scale.
• Proven experience managing managers and leading multiple high-performing infrastructure/platform/SRE teams in a fast-paced, high-growth environment.
• Hands-on experience with Infrastructure-as-Code (e.g., Terraform, Pulumi) and CI/CD (e.g., GitHub Actions, GitLab CI, Jenkins).
• Familiarity with GitOps workflows (e.g., Flux CD, Argo CD, Helm).
• Deep expertise in Kubernetes (e.g., EKS, GKE) and distributed systems.
• Strong observability background and experience raising reliability standards via SLOs/SLIs and observability-as-code.
• Familiarity with observability stack/tools including Prometheus, VictoriaMetrics, Loki, ELK, Grafana, and OpenTelemetry.
• Openness to learning ML infrastructure and model serving (no prior ML experience required).
• Interest/experience with high-performance AI workloads, including troubleshooting ML pipelines and serving.
• Experience with GPU infrastructure, including fractional GPU provisioning and multi-node model serving (e.g., H100/B200).
• Experience with incident management platforms (e.g., incident.io, PagerDuty) and building AI-assisted incident triage.
• Experience scaling an SRE practice: runbook standards, self-healing automations, and systematic mitigations.

Nice to have

• Experience with GPU/multi-node model serving specifically.
• Experience building AI-assisted tooling for incident response.