Senior Site Reliability Engineer

Location: United Kingdom (Remote)

---

About the Position

Runware is building high-performance infrastructure and products to power the world's intelligence. Our platform enables developers and businesses to run fast, scalable inference across image, video, and emerging modalities, while our Serverless platform allows customers to deploy and scale their own AI models on production-grade GPU infrastructure.

As a Site Reliability Engineer at Runware, you will help ensure these systems remain reliable, performant, and resilient as we scale. This is a highly technical, hands-on role working across software, infrastructure, and production operations to improve observability, reduce incidents, eliminate operational toil, and build lasting improvements across complex distributed systems.

---

Responsibilities

• Own and improve the reliability, availability, and performance of critical production services across the Runware platform
• Define and evolve our reliability practices, including SLIs, SLOs, alerting, observability, and production-readiness standards
• Investigate complex production issues across distributed systems, APIs, networking, queues, databases, and GPU-backed workloads, participating in our engineering on-call rotation
• Lead and contribute to incident reviews and RCAs, turning recurring failure modes into lasting engineering improvements
• Reduce operational toil through automation, automated remediation, and improvements to deployment safety, recovery, and system resilience
• Work closely with Engineering and DevOps teams on capacity planning, performance, scaling, and architectural improvements as the platform grows

---

Requirements

• Strong experience operating and troubleshooting production systems at scale in an SRE, Production Engineering, Platform Engineering, or similar role
• Strong understanding of distributed systems and comfort debugging across applications, databases, queues, containers, networking, and infrastructure
• Experience designing and operating observability systems using metrics, logs, and distributed tracing
• Understanding of SRE principles including SLIs, SLOs, error budgets, capacity planning, incident management, and reducing operational toil
• Experience with Kubernetes, containers, IaC, and automated deployment practices, alongside the ability to write software and automation using languages such as Python, Go, or PHP
• Strong ownership of production problems and comfort participating in an engineering on-call rotation, taking issues from initial investigation through to long-term remediation

---

Nice to Have

• Experience operating high-throughput or low-latency APIs and distributed systems
• Experience with bare-metal infrastructure, GPU environments, or AI and ML workloads
• Experience with RabbitMQ or other distributed messaging and queueing systems
• Experience operating MySQL, Redis, ClickHouse, or similar production data systems
• Experience with global traffic management, load balancing, CDN platforms, and hybrid infrastructure environments
• Experience building automated scaling, capacity management, or self-healing systems

---

We Offer

• 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

---

About the Company

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.

We move quickly and hold a high bar, but we also believe sustainable performance matters. After major releases and milestones, we create space for the team to properly unplug, recharge, and come back with the energy to tackle what's next.