Staff Engineer – GPU Driver & System Software

Staff Engineer – GPU Driver & System Software

Our client is a global fabless semiconductor company enabling nearly 2 billion connected devices a year. They are a market leader in developing innovative systems-on-chip (SoC) for mobile device, home entertainment, connectivity and IoT products, and hold the number one position in Wi-Fi supply across broadband, retail routers, consumer electronics devices and gaming, with Wi-Fi 6 chipsets powering the latest networking equipment for faster computing experiences.
As a market leader in SoC design, the company’s GPU IP team is committed to industry-leading, feature-rich and PPA-competitive GFX IP optimisation, customisation and development. The GFX IP is deployed not only in flagship and mainstream mobile SoC, but also serves as fundamental technology for adjacent markets including laptop, IoT, AI, VR/AR and automotive.
The team is now hiring GPU talent across all levels, including Architecture, SW Driver, Compiler, Performance, Power and Model engineers, to join their site in Cambridge.

About The Role

Bring your GPU driver expertise and play a key role in shaping the future of next-generation GPU technologies. In this role, you will collaborate closely with Architecture, Micro-architecture, Compiler, and Model teams to unlock maximum performance from our silicon and drive cutting-edge GPU innovation.
This is a full-stack GPU software opportunity, offering exposure across the entire stack—from industry-standard graphics and compute APIs to kernel-mode drivers, GPU firmware, and performance optimization. You will contribute to hardware/software co-design efforts, ensuring seamless integration and optimal performance across all layers.
If you are passionate about low-level systems, performance tuning, and pushing the limits of GPU capabilities, this role offers a unique platform to make a direct impact on advanced GPU design and development.

Roles And Responsibilities:-

• API Layer: Architect, develop, and optimize features for industry-standard APIs including Vulkan, DirectX, OpenGL ES, and OpenCL.
• Kernel & Firmware: Work deep in kernel-mode drivers and GPU firmware to improve hardware control, stability, scheduling, memory management, and execution efficiency.
• Performance: Identify, analyze, and eliminate bottlenecks across the stack — including driver overhead, memory bandwidth, GPU scheduling, compute throughput, and power/performance tradeoffs.
• Architecture Collaboration: Partner closely with Architecture, Micro-architecture, Compiler, and GPU Model teams to influence next-generation GPU design and ensure the software stack fully leverages the hardware.
• Technical Leadership: Lead complex debug efforts, guide design decisions, mentor engineers, and help raise the technical bar across the GPU driver team.
• No Silos: You are not restricted to only the API layer, kernel driver, firmware, or performance. You can work across the entire GPU software stack.
• Shape the Hardware: Your software insights will directly influence next-generation GPU architecture and micro-architecture.
• High-Impact Work: Your contributions will help turn silicon capability into real-world graphics, compute, and AI performance.

Requirements

• Experience of building GPU drivers, graphics systems, or low-level systems software.
• You are fluent in C/C++ and comfortable working close to hardware.
• You have deep expertise in one or more industry-standard APIs such as Vulkan, DirectX 12, OpenCL, or OpenGL ES.
• You understand GPU internals at a deep level, including memory hierarchies, command submission, scheduling, synchronization, pipeline architecture, and performance bottlenecks.
• You enjoy working across boundaries — from API design to kernel drivers, firmware, compiler interaction, and hardware architecture.

Main Requirements and Qualifications
Preferred Qualifications (Nice to Have)

• Background in GPU performance analysis, firmware, virtualization, compiler, or runtime optimization for GPUs or accelerators.
• Familiarity with ML/AI workloads, DNN operators and their mapping onto GPU or accelerator architectures.
• Experience collaborating with architects, micro-architects, compiler, and model teams.