6 months ago
London, United KingdomSenior
Responsibilities
- Build infrastructure that orchestrates heterogeneous compute across models, workflows, and silicon.
- Develop high-performance systems, low-level performance engineering, inference infrastructure, orchestration, or distributed systems.
- Bring up hardware and develop kernels or accelerator programs for novel accelerators.
- Create simulations, models, and workloads for heterogeneous compute systems.
Requirements
- Exceptional engineering skills and a desire to work on difficult AI infrastructure problems.
- Experience in high-performance systems, low-level performance engineering, inference infrastructure, orchestration, distributed systems, hardware bring-up, kernel development, accelerator programming, simulation, modelling, or workload design.
Benefits
- The team is based in London and works across the full depth of the technology stack.
- This is a general interest application reviewed on an ongoing basis rather than a specific role.
