Inference Engine Development - Member of Technical Staff

About Us

We’re living through a Cambrian explosion of intelligence: new models and new chips, each specialised for different tasks, are arriving all at once. The result is a new era for AI, one of radical heterogeneity.

Callosum is the Intelligent Systems Company. We believe the next generation of AI won't be defined by any single model or chip, but by intelligent systems in which hardware and intelligence co-evolve. We are building the infrastructure that unifies heterogeneous compute across the full stack. This opens a new axis of scaling intelligence: a dynamic system that tailors itself to what each workload actually needs, whether that's speed, cost, precision, or whatever unit comes next.

The last era scaled on a different bet: one bigger model, more of the same chip, more data. That bet is running into structural limits. Frontier models offer extraordinary capability at unsustainable cost, one that today's monolithic infrastructure was never designed to serve.

Our founding principle is that intelligence comes from many specialised systems working together, not from any single component. We build the software orchestration layer that co-evolves models, workflows and silicon into one system, delivering inference tailored to every workload, and demonstrating orders-of-magnitude leaps in capability and cost.

Because our software spans the full stack, our engineering team works directly with heterogeneous accelerators and frontier silicon, including Cerebras, d-Matrix, Intel, NVIDIA, AMD, Normal Computing, Tenstorrent, GreatSky, and Mixx. We are not stopping at today's chips: each new generation of silicon unlocks algorithms that couldn't run before, and we intend to be first to them, every time. If we get it right, it will belong to everyone building on it - not to any single vendor.

In our latest funding round, we raised $100M, led by Atomico with participation from Plural, DCVC and the UK Sovereign AI Fund’s first investment. With this, we are building the infrastructure for the next era of intelligence.

We are engineers and scientists based in London, working across the full depth of the stack. We are curious, intellectually honest, and building what doesn't exist yet. If you thrive on uncharted territory and are energised by the scale of the challenge, we'd love to hear from you.

ABOUT THE ROLE

Callosum believes that orders of magnitude improvements in AI systems will come through application-aware orchestration across heterogeneous hardware. We are building infrastructure that treats the full landscape of compute as a unified, co-evolving system, extending beyond the assumptions of conventional GPU-centric inference.

Modern inference engines are built around particular assumptions about hardware, memory, and execution. This role extends existing frameworks and develops custom inference technologies to enable efficient execution across heterogeneous accelerators. You will work across scheduling, memory management, parallelism, and execution strategies, adapting inference systems to emerging hardware capabilities while integrating them with Callosum's broader orchestration stack.

WHAT YOU'LL BUILD

• Extend inference systems such as SGLang and vLLM, alongside developing custom inference engine technologies.
• Develop hardware-aware execution strategies that exploit the capabilities of different accelerator architectures.
• Optimise inference scheduling, batching, attention execution, and memory management for different workload characteristics.
• Explore new approaches to parallelism, disaggregation, and efficient execution across heterogeneous resources.
• Develop interfaces that expose inference engine capabilities and execution state to higher-level orchestration systems.

WHAT SETS YOU APART

• Deep familiarity with SGLang, vLLM, or comparable inference frameworks and their internal execution mechanisms.
• Strong understanding of how batching, attention implementations, caching, and scheduling interact to determine inference performance.
• Experience with high-performance ML inference systems, including Python, C++, CUDA, or similar technologies.
• Familiarity with techniques such as PagedAttention, chunked prefill, prefix caching, or optimised attention kernels.
• Strong systems engineering instincts and an ability to reason across inference software and hardware boundaries.

What We Offer

• 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.