Head of Infrastructure Operations - Runware

About Runware

Runware is the AI inference platform that builds and operates its own infrastructure, end to end. One API gives developers access to image, video, audio, 3D and language models, and our Sonic Inference Engine runs them on hardware we designed ourselves: custom servers, custom boards and a closed-loop, water-free cooling system, packed into Sonic Inference Pods — roughly 1 MW of liquid-cooled GPU compute in a 20-foot container that can be sited wherever power is cheap and available.

This is why infrastructure at Runware is the product, not a cost center. Our edge is that we run inference 30–90% cheaper per GPU-hour than our peers, and that edge is earned in the data center: in how fast we can stand up a new site, how tightly we run our fleet, and how little downtime our customers ever see.

The Role

As Head of Infrastructure Operations, you'll own the physical and operational backbone of Runware: the servers, storage and networking across every site we run, and the team that keeps them running. You'll take us from a handful of pods to a global fleet, and you'll decide how that fleet is built, provisioned, monitored, maintained and scaled.

This is a hands-on leadership role. You'll set the operating model and hire the team, but you'll also be in the terminal, in the rack and in the incident channel when it matters.

You'll report to Risto Haukioja, Head of AI Infrastructure and work closely with the hardware, platform and inference engineering teams, and with our data center, power and hardware partners.

What You'll Do

• Build and run global infrastructure operations across our pod sites in the US and Europe: site bring-up, rack and stack, cabling, power and cooling integration, burn-in and acceptance, through to steady-state operations and decommissioning.
• Own the server, storage and network layers of the fleet end to end: Linux fleet management, bare-metal provisioning and imaging, firmware and driver lifecycle, and high-throughput storage.
• Define how a new site goes live and turn pod deployment into a repeatable, documented, largely automated playbook.
• Set and hit reliability targets. Own capacity planning, monitoring, alerting, on-call, incident response and post-incident reviews.
• Hire, lead and develop a high-performance team of data center, systems and network engineers across time zones.
• Manage colocation, power, connectivity and hardware vendors and partners.
• Use AI to accelerate the work: automate runbooks, triage and tooling with LLM-based agents.
• Own the operational side of security and compliance for our physical infrastructure.

What We're Looking For

• 15+ years in infrastructure engineering and operations, with at least several of those leading the function at a company that runs its own hardware at scale.
• A track record of building infrastructure operations across multiple sites, regions or countries.
• Deep, current, hands-on Linux expertise: kernel and driver behaviour, performance tuning, bare-metal provisioning, configuration management and fleet automation.
• Strong storage fundamentals: NVMe, distributed and parallel file systems, object storage, and designing for high throughput and IOPS.
• Strong networking fundamentals: L2/L3 design, BGP, data center fabrics, and high-bandwidth interconnects.
• Experience running high-performance teams and building a strong on-call and incident culture.
• You use AI to accelerate your own output every day.
• Comfortable owning outcomes in a fast-moving, ambiguous environment.
• Able to travel to sites in the US and Europe as needed.

What We Offer

• A rare mandate to build global AI infrastructure operations from the ground up.
• Meaningful stock options.
• Remote-first collective, meeting in person twice a year.
• Generous paid time off, including vacation, sick days and public holidays.
• Paid maternity, paternity and caregiver leave.