DevOps Team Lead

Runware’s infrastructure is the foundation that enables our teams to deliver AI to the world. As DevOps Team Lead, you’ll turn complex, hardware-driven systems into streamlined, developer-friendly platforms.

You’ll define how we automate deployments, orchestrate GPUs at scale, and observe workloads in real time. You’ll build systems that detect and recover from issues before users notice, and work closely with engineering and product teams to make shipping faster, safer, and more predictable.

You’ll shape the foundation that lets teams move fast with confidence, building infrastructure that is dependable, observable, and designed to scale.

You thrive at the intersection of infrastructure and innovation. You enjoy unravelling complex systems, tuning performance, and engineering reliability into everything you build. You lead through clarity and example, not process, and elevate the teams around you by simplifying the hard things.

You take pride in building systems that are resilient by design and empowering the engineers who depend on them. You understand that reliability is never accidental; it is built through intent, consistency, and a culture that values doing things right.

• Providing technical and people leadership to a small DevOps team
• Lead the design and operation of Runware’s infrastructure and orchestration systems
• Build automation and tooling to streamline model deployments, scaling, and hardware utilisation across distributed nodes
• Drive observability, alerting, and reliability practices to detect and resolve issues quickly and proactively
• Collaborate with engineers to optimise throughput, latency, and platform performance at every layer of the stack
• Develop and maintain infrastructure as code and deployment automation to ensure consistency and reproducibility across environments
• Establish and continuously evolve incident management, post-mortems, and reliability reviews as core engineering practices
• Mentor and coach engineers to think operationally, designing systems that fail gracefully and scale predictably
• Champion forward-looking improvements to our orchestration layer, hardware management, and overall infrastructure efficiency

• Have experience operating production systems on bare metal or hybrid environments such as HPC or GPU clusters, optimised for performance and low latency
• Are comfortable writing automation and systems tooling in Python, Go, or similar languages
• Understand container runtimes like Docker and containerd, and have built or worked with orchestration systems beyond Kubernetes
• Are fluent in observability and debugging practices across distributed systems, using logs, metrics, traces, and profiling to drive insight and reliability
• Care deeply about reliability, efficiency, and engineering quality, and know how to embed those values into team culture and everyday practice
• Thrive in fast-moving, evolving environments where impact is measured by how much better systems and teams perform over time

We’re a remote-first collective, meeting in person twice a year to plan, brainstorm, celebrate wins, and enjoy some face-to-face time. We have core hours for cooperative working and calls, but outside of that your calendar is yours. Work the hours that let you perform at your peak while also building a healthy life.

Our release cycles are fast and intense, but they’re followed by real downtime. After big pushes we expect the team to unplug, recharge, and come back ready & stronger than ever for the next leap.

• Generous paid time off – vacation, sick days, public holidays
• Meaningful stock options – share in the upside you create
• Remote-first setup – work from home anywhere we can employ you
• Flexible hours – own your schedule outside core collaboration blocks
• Family leave – paid maternity, paternity, and caregiver time
• Company retreats – twice-yearly gatherings in inspiring locations

Please note: We are unable to offer visa sponsorship in the UK at this time. Candidates must have existing right to work in the UK.