Most AI infrastructure is built for batch: send a query, wait, get a response, reset. Powerful, but transactional. AI is becoming interactive — sessions that hold state, models that stay alive between turns, generation that responds as it runs — and the infrastructure to deliver that at scale doesn't really exist yet.
The bottleneck isn't the models anymore. It's the infrastructure underneath them.
uRun is the inference cloud for interactive AI: the compute layer that makes real-time, stateful inference possible at scale. We came out of stealth in April 2026, are backed by top-tier investors, and are founded by Keegan McCallum, who scaled inference infrastructure for some of the most demanding generative AI workloads in production.
We're an infrastructure company. We build the layer that model labs, builders, and research teams ship on top of.
Reliability at uRun isn't a feature — it's the product. When model labs and production teams build on top of our inference platform, they are trusting us with their uptime, their latency, and their users. As our Site Reliability Engineer, you will own that trust end-to-end.
This is a founding SRE hire. You will define the reliability culture from scratch: the observability stack, the incident response playbooks, the SLOs, and the on-call process. You will work directly with infrastructure and platform engineers to close the gap between what we ship and what stays up.
Define and own SLOs and error budgets across uRun's inference platform and supporting infrastructure
Build and maintain the observability stack end-to-end: metrics, logging, tracing, and alerting across a distributed GPU compute environment
Lead incident response: detection, triage, resolution, and blameless postmortems that drive lasting fixes
Partner with ML infrastructure engineers to embed reliability into the deployment pipeline from day one
Design and maintain runbooks, on-call rotations, and escalation paths as the team scales
Drive capacity planning and traffic management across heterogeneous compute to protect latency and availability under load
Identify and eliminate toil through automation, building systems that scale without scaling the team proportionally
7+ years in site reliability, production engineering, or infrastructure engineering in a high-availability, low-latency environment
Deep experience owning SLOs, error budgets, and on-call processes in production at scale
Strong observability background: you have built or owned monitoring stacks (Prometheus, Grafana, Datadog, or equivalent) and know what good alerting looks like
Proven incident response experience: you have led real incidents under pressure and written postmortems that actually changed behaviour
Hands-on with Kubernetes and cloud infrastructure (AWS preferred): you can debug a failing pod and a misconfigured VPC in the same afternoon
Strong software engineering fundamentals: you write automation, not just runbooks
Comfortable operating as the first and only SRE, setting standards without a template to follow
Experience supporting GPU compute or ML inference infrastructure in production
Familiarity with stateful workloads, long-running sessions, or streaming inference systems
Exposure to multi-tenant platforms where isolation, noisy neighbour problems, and billing-aware scheduling matter
Prior founding or sole SRE experience at an early-stage company
Competitive salary and meaningful equity in an early-stage AI infrastructure company. The band above is our target; for an exceptional candidate we'll go higher. Equity is real — you're early, and the grant reflects that.
Health, dental, and vision — full coverage
401(k) — company-supported retirement savings
FSA/HSA — flexible spending accounts for healthcare costs
Paid time off — we trust you to manage your time
Top-tier tooling — access to the best AI tools available: Claude, Codex, Kimi, and whatever else helps you move faster
MacBook Pro and AirPods — the hardware you need, on us
We build the stage, not the show. We're an infrastructure company, a developer-tools company, and a production partner for model labs, and focus is a deliberate choice we've made and hold to.
Day-to-day, that means a small team, a high bar, and real ownership. You won't wait for permission or inherit a backlog of someone else's decisions, in a founding security role, the function is what you make it.
It also means ambiguity: priorities shift, not everything is documented, and you'll often be the person who decides what "secure enough, for now" means. That suits some people and not others, and we'd rather you know that before you apply.
Job details are sourced from the employer's original posting.
Open job postingAbout the company
uRun is building the inference cloud for interactive AI, addressing the limitations of current batch-oriented infrastructure for stateful and real-time AI applications.