ABOUT BASETEN
Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our Series E, backed by investors including BOND, IVP, Spark Capital, Greylock, and Conviction. Join us and help build the platform engineers turn to to ship AI products.
THE ROLE
As an Infrastructure Ops Engineer at Baseten, you are the operational engine of our global infrastructure. You will sit at the intersection of technical customer success and infrastructure engineering, partnering closely with our SRE and FDE teams to execute the complex hardware lifecycles that power our fleet.
This role is designed for high-energy, detail-oriented individuals who thrive on technical coordination and operational excellence. You aren't just managing clusters; you are acting as the technical glue between our customers' needs and our hardware reality, ensuring that high-level capacity strategies are translated into boots-on-the-ground results.
While you will be hands-on with Kubernetes and cloud-native tools, your success is measured by your ability to project-manage the resolution of capacity puzzles, ensuring our platform remains reliable, observable, and ready for the next massive AI deployment.
EXAMPLE INITIATIVES
- The "Lost Node" Investigation: Debugging cluster-level blockers to solve why pods aren't scheduling despite available capacity
- Regional Compliance Guard: Auditing and correcting scheduling policies to ensure customer data stays within specified geographical constraints (e.g., EU-only vs US-only)
- High-Stakes Maintenance Orchestration: Coordinating critical maintenance cycles both externally (with vendors) and internally (with Baseten SREs) to evacuate workloads from unhealthy nodes and integrate replacement hardware with zero customer disruption
RESPONSIBILITIES
- Fleet Maintenance: Manage daily node operations including tainting/untainting, node draining, and PVC repairs to ensure GPU fleet health and operational cost control
- GTM & Capacity Fulfillment: Partner with Sales and account teams to scope and fulfill customer capacity requests, translating complex timelines into concrete infrastructure actions and clear ETAs
- Process & Observability Engineering: Identify recurring gaps in the capacity lifecycle (intake, triage, comms) and drive fixes by defining lightweight processes and improving system observability
- Technical Orchestration: Act as the operational bridge between SRE and Infra teams, executing discrete changes and verifying system status during high-stakes maintenance windows
- Technical Documentation: Contribute to the internal knowledge base for GPU-specific issues (H100/A100/B200) to accelerate future incident resolution
- Automation & Tooling: Identify repetitive workflows and partner with engineering to build scripts, dashboards, and internal tools that reduce manual intervention and shorten time-to-mitigation
- Knowledge Excellence: Maintain a living database of GPU-specific intelligence (H100/B200) and market moves to accelerate incident resolution and support strategic briefings for leadership
REQUIREMENTS
- Bachelor's or Master's degree in Computer Science, Engineering, or a related field
- 2+ years of professional work experience, ideally in a customer-facing technical role or as a junior SRE/Cloud Engineer
- Strong familiarity with Kubernetes and the lifecycle of cloud-based container orchestration
- Strong ownership mindset and attention to detail, demonstrated through fast detection, clear communication, and reliable follow-through
- Demonstrated ability to communicate complex technical blockers clearly to both internal engineering teams and external vendors
- Preference for SF or NYC-based candidates to foster a close-knit "family" atmosphere in the office