Staff Engineer, Inference Platform - Architecture

Artificial intelligence scaled on a bet - that bigger models, more identical chips, and more data would keep delivering. As problems grow more complex and the requirements of intelligence more diverse, that bet is breaking down. The next era belongs to heterogeneous intelligence: diverse models on diverse chips, each with distinct strengths, co-evolving into systems of capability unreachable by any single model or accelerator.

Callosum is the Intelligent Systems company. We built the infrastructure to make that possible. Our co-evolution engine optimises simultaneously across workflows, agents, and silicon. We launched in early 2026 showing orders of magnitude improvements in performance and a shift in the cost-performance frontier that no single chip or model provider can provide.

We believe intelligence comes from the system, not the model.

We are scientists and engineers solving what others consider impossible. If you thrive on hard problems, and are passionate and energised by the scale of the challenge, we'd love to hear from you.

Heterogeneous intelligence has to be served. An architecture designed in research is only useful if it can be exposed to customers as a single, fast, reliable endpoint, one that hides the complexity of many models, chips, and coordination patterns behind a single interface that customers already know. That platform is what this role builds.

You will own the architecture and ongoing evolution of the platform that serves Callosum's Intelligent Systems to enterprise customers. Customers query a workflow; the platform resolves it into a coordinated execution across heterogeneous systems, with latency, throughput, and reliability guarantees expected from frontier inference. Designing how that resolution happens - and keeping the design coherent as intelligent systems grows - is the core work.

Concretely, you will design the API surface itself, the orchestration layer behind it, the contracts between the platform and the systems it serves, and the operational primitives - durable execution, fault isolation, multi-tenancy, observability - that make the whole thing dependable. As the platform grows by orders of magnitude over the coming year, the work shifts from building the operational foundation to defending it under conditions most teams never encounter. The decisions you make now will either hold under that load or break under it.

You will work closely with the engineers designing new intelligent systems, who depend on the platform to expose their work, and with the teams running our heterogeneous backends. You will partner directly with the Staff Engineer responsible for platform reliability, setting the technical direction of the platform.

Who We Are Looking For

This is a senior role and the bar is correspondingly specific. We expect the person in this role to set the technical direction of the platform. We're looking for someone who has done this kind of work before, at this kind of scale, and is ready to do it again with much more on the line.

• Demonstrated experience designing and shipping distributed systems at production scale, as the engineer responsible for the architecture rather than adjacent to it.

• Deep fluency with the components of modern serving infrastructure: stateless and stateful services, durable workflow orchestration, queueing, autoscaling, multi-tenancy.

• Deep experience designing APIs that have lived in production.

• The judgment to know which decisions are reversible and which are not.

What Stands Out

• You have built or substantially evolved an LLM serving platform, an agent runtime, or comparable inference infrastructure handling billions of tokens or requests.

• You understand the landscape of accelerators and how serving patterns change across them.

• You have led architectural decisions whose effects survived your tenure.

• Open-source contributions to relevant infrastructure projects, or production systems whose scale and complexity you can speak to in detail.

• Competitive Salary, determined by skills and experience

• Equity & Ownership

• Private healthcare

• We offer Visa sponsorship and relocation benefits to hire the best in the world

• We work in person at our London office. You'll have the tools, space and setup to do your best work, and if you have specific needs, just tell us

We're committed to building an inclusive workplace where everyone feels welcome, and believe in equal opportunities for all.