A

Founding Engineer - Hadron Runtime Infrastructure

ayoob ai • United Kingdom
Remote Visa Sponsorship Relocation
This Job is No Longer Active This position is no longer accepting applications
AI Summary

First engineering hire at Hadron, building a hardware-aware dispatch runtime for AI workloads across WebGPU, Web Workers, and CPU. Design compute kernels, dispatch scoring logic, memory pooling, and pipeline caching while maintaining cross-vendor GPU compatibility. Requires shipped production WebGPU/ML systems experience and strong runtime architecture instincts.

Key Highlights
First engineering hire at Hadron
Hardware-aware dispatch runtime for AI workloads
Cross-vendor GPU compatibility (NVIDIA, AMD, Intel, Apple, Qualcomm)
OSS reference layer development
Patent filing opportunity
Key Responsibilities
Design and implement compute kernels across WebGPU, Web Workers, and CPU tiers
Build dispatch scoring logic across discrete, integrated, and unified memory GPUs
Architect memory pooling, pipeline caching, and buffer reuse
Maintain cross-vendor compatibility across NVIDIA, AMD, Intel, Apple, and Qualcomm
Drive the OSS reference layer that supports developer adoption
Contribute to patent filings
Technical Skills Required
WebGPU Web Workers CPU C++ Rust systems-level JavaScript Python ML inference
Benefits & Perks
Real equity
UK visa sponsorship
Relocation assistance
Nice to Have
ML inference background

Job Description


Founding Engineer, Hadron


Ayoob AI is a UK-based AI company with active engagements including UK Government frameworks. Hadron is our infrastructure division, building a hardware-aware dispatch runtime that routes AI workloads between WebGPU, Web Workers, and CPU. Five UK patent applications filed earlier this year. 5,500 lines of WebGPU code, 447 tests passing. Pre-seed round opening.


About the role:

First engineering hire at Hadron. You ship the first commercial version of the runtime alongside the founder.


Responsibilities:

- Design and implement compute kernels across WebGPU, Web Workers, and CPU tiers

- Build dispatch scoring logic across discrete, integrated, and unified memory GPUs

- Architect memory pooling, pipeline caching, and buffer reuse

- Maintain cross-vendor compatibility across NVIDIA, AMD, Intel, Apple, and Qualcomm

- Drive the OSS reference layer that supports developer adoption

- Contribute to patent filings


What we are looking for:

- Shipped production WebGPU or ML systems work

- Strong runtime architecture instincts

- Comfort with C++, Rust, or systems-level JavaScript, Python

- ML inference background is a plus, not required

- Self-directed, comfortable with ambiguity


On the table:

- Founding Engineer title

- Real equity, number open to negotiation

- Name on patents you contribute to (we file aggressively)

- UK visa and relocation if needed, fully remote also fine


To apply: [email protected]


Similar Jobs

Explore other opportunities that match your interests

Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Mid-Senior level

IC Resources

United Kingdom

Full-Stack Software Engineer

Programming
•
9h ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

Bending Spoons

United Kingdom
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Mid-Senior level

Understanding Recruitment

United Kingdom

Subscribe our newsletter

New Things Will Always Update Regularly