AI inference today is slow, expensive, and stateless. Send a query, wait, get a response, reset. That's fine for batch, but AI is becoming interactive, and interactive means inference has to respond instantly, hold context across a session, and be steerable in real time.
Nobody had built infrastructure that does all three at once. The bottleneck isn't the models. It's the runtime underneath them.
uRun — Universal Runtime is the layer that makes real-time, stateful inference possible. Our platform lets AI respond instantly, hold context across a session, and be directed as it runs.
We prove it through the hardest problem in the stack: real-time AI video generation. Not pre-rendered clips. Not queued jobs. Live, steerable, continuous video that responds as you speak. Solve that, and the rest of the inference stack follows — and that's what we've done. We're an infrastructure company; we build the layer model labs, builders, and research teams ship on top of.
You'll build the services, APIs, and core application systems that power uRun's runtime the software layer that turns our real-time inference platform into something product and applied AI teams can actually build on.
This is not a conventional CRUD backend role. The work centres on low-latency, high-throughput systems: real-time interaction, evolving session state, and request handling that stays reliable under heavy compute and concurrency. You'll work closely with product, infrastructure, and applied AI teams, in an early-stage environment where the architecture is still being set.
Build and maintain backend services, APIs, and internal platform components that power uRun's real-time inference runtime
Design systems for real-time interaction, evolving session state, and scalable request handling across production environments
Partner with infrastructure and platform engineers to keep services observable, reliable, and efficient under heavy compute and concurrency
Translate experimental AI capabilities into robust, user-facing software, working closely with product and applied AI teams
Shape architecture decisions on data flow, service boundaries, performance optimisation, and fault tolerance for interactive systems
Raise engineering quality through testing, monitoring, code review, documentation, and sound operational practice
7+ years building and shipping backend software in production
Proficiency in one or more backend languages — TypeScript/Node.js or Python, Go,
Experience designing APIs, service-oriented systems, and distributed application components
Solid understanding of cloud infrastructure, containers, and modern deployment workflows
Ability to reason about performance, concurrency, reliability, and debugging in complex systems
Experience with real-time, interactive, streaming, or latency-sensitive systems, this is central to the role, not a bonus
WebRTC or WebSockets for real-time communication
AI infrastructure, inference-adjacent systems, media pipelines, or event-driven architectures
Kubernetes, observability tooling, and hands-on production operations
Early-stage startup experience — owning problems end-to-end and moving quickly with limited scaffolding
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
You'd join an early team building a genuinely new category of real-time AI infrastructure and product. You'd work directly with the founder and senior technical leadership, with real influence over architecture, developer velocity, and the shape of the product itself, working at the intersection of backend systems, platform engineering, and interactive AI.
It also means ambiguity. We're early: there's limited scaffolding, priorities shift, and you'll often be setting architecture before there's a playbook to follow. That's a real part of the job, and it suits some people far more than others. We'd rather you know it going in.
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.