Senior GPU Architect: Lead Next-Gen AI Compute

MRL Consulting Group | Global Niche Technology Recruitment; England; On-site; GBP 120,000 - 150,000; Full time

Job summary

MRL Consulting Group represents a leading global technology organisation seeking a Principal GPU Architect to lead the development of next-generation mobile GPU and AI compute architectures.

The role requires 15+ years in GPU/AI accelerator or heterogeneous compute architecture, with expert knowledge of GPU microarchitecture and AI tensor processing. You will drive architecture from concept to tape-out, coordinating with CPU and software teams.

Qualifications

• 15+ years’ experience in GPU, AI accelerator or heterogeneous compute architecture.
• Deep knowledge of GPU microarchitecture, including SIMD/SIMT, scheduling and memory systems.
• Strong understanding of AI acceleration and tensor/matrix processing.
• Expertise in performance modelling, power analysis and system-level architecture.
• Strong technical leadership and cross-functional communication skills.

Responsibilities

• Define GPU/NPU architectures optimised for performance, power and silicon area.
• Analyse graphics and AI workloads and develop future-focused hardware and software architectures.
• Lead GPU microarchitecture, including execution pipelines, scheduling, cache and memory systems.
• Optimise on-chip interconnect and resource sharing for heterogeneous workloads.
• Collaborate with CPU, AI software and system architecture teams.
• Drive architecture from concept through to tape-out and support silicon bring-up.

Skills

GPU architecture

Hardware design

Performance modelling

Leadership

Cross-functional collaboration

Job description

We are recruiting on behalf of a leading global technology organisation for a Principal GPU Architect to lead the development of next-generation mobile GPU and AI compute architectures.

Key Responsibilities

• Define GPU/NPU architectures optimised for performance, power and silicon area.
• Analyse graphics and AI workloads and develop future-focused hardware and software architectures.
• Lead GPU microarchitecture, including execution pipelines, scheduling, cache and memory systems.
• Optimise on-chip interconnect and resource sharing for heterogeneous workloads.
• Collaborate with CPU, AI software and system architecture teams.
• Drive architecture from concept through to tape-out and support silicon bring-up.

Key Requirements

• 15+ years’ experience in GPU, AI accelerator or heterogeneous compute architecture.
• Deep knowledge of GPU microarchitecture, including SIMD/SIMT, scheduling and memory systems.
• Strong understanding of AI acceleration and tensor/matrix processing.
• Expertise in performance modelling, power analysis and system-level architecture.
• Strong technical leadership and cross-functional communication skills.