Senior Systems Architect - DX-1 AI Inference Platform in London

Senior Systems Architect - DX-1 AI Inference Platform in London

London Full-Time 80000 - 100000 Β£ / year (est.) No working from home possible
PassFort

At a Glance

  • Tasks: Lead the development of the runtime and serving stack for cutting-edge AI inference.
  • Company: Join OLIX, a leader in innovative AI technology.
  • Benefits: Attractive salary, flexible work options, and opportunities for professional growth.
  • Other info: Collaborative environment with cross-functional teams and exciting challenges.
  • Why this job: Be at the forefront of AI technology and make a significant impact.
  • Qualifications: Expertise in C/C++ and strong systems thinking required.

The predicted salary is between 80000 - 100000 Β£ per year.

OLIX is seeking an Architect/Staff/Senior Systems Software Engineer to own the runtime and serving stack for the DX-1 accelerator, enabling production inference across disaggregated hardware. You will extend the stack from PyTorch/JAX to the metal, across the runtime, network, and accelerator boundary.

This whole-stack role requires deep C/C++ expertise, strong systems thinking, and the ability to lead cross-functional initiatives with hardware, compiler, and modeling teams to optimize serving.

Senior Systems Architect - DX-1 AI Inference Platform in London employer: PassFort

At PassFort, we pride ourselves on being an exceptional employer, offering a dynamic work culture that fosters innovation and collaboration. Our commitment to employee growth is evident through continuous learning opportunities and the chance to make a meaningful impact in the healthcare sector, particularly in our vibrant location that thrives on community engagement and support for NHS initiatives.

PassFort

Contact Details:

PassFort Recruitment Team

We think you need these skills to ace Senior Systems Architect - DX-1 AI Inference Platform in London

C/C++ Expertise
Systems Thinking
Cross-Functional Leadership
Runtime Development
Network Optimization
Accelerator Integration
PyTorch