FY27 Intern - GPU Compiler - 3 months, Cambridge
Qualcomm
·Today
- Location
- Cambridge, England,GB, GB
- Type
- Internship
- Seniority
- Internship
- Education
- PhD
- Source
- Eightfold
Description
##
Company:
Qualcomm Technologies International Ltd
## Job Area:
Interns Group, Interns Group > Interim Intern
General Summary:
Opportunity Overview
We are looking for a curious, hands-on and self-motivated intern to join the GPU Compiler team in Cambridge for a 3-month placement.
Qualcomm Adreno™ GPUs power graphics, compute and AI workloads in billions of devices, from smartphones and XR headsets to laptops and automotive platforms. The GPU compiler is a critical part of this stack. It translates shaders and compute kernels written in high-level languages and intermediate representations into efficient machine code for our GPU architecture. Compiler decisions directly affect performance, power and memory bandwidth, which makes the compiler central to the product experience.
During the internship you will work under the guidance of experienced compiler engineers on a real part of the GPU compiler toolchain. Depending on your background and the needs of the project, the work may involve optimisation passes, code generation, performance analysis of graphics and compute workloads, or compiler test and validation infrastructure.
Representative Projects
- Design, implement and evaluate compiler optimisations targeting GPU shader and compute workloads.
- Investigate code-generation strategies for GPU-specific concerns such as thread divergence, occupancy, register pressure and latency hiding.
- Profile and analyse the performance of graphics shaders and compute kernels, identify compiler-related bottlenecks and propose improvements.
- Extend compiler front-end or IR lowering support for graphics and compute languages and intermediate formats (e.g. SPIR-V, GLSL, HLSL, OpenCL).
- Develop tools for compiler testing, correctness validation, fuzzing or performance regression tracking.
- Explore compiler techniques for emerging GPU workloads, including ML inference and compute shaders.
The exact project will be chosen to match the candidate's background and interests and the technical priorities of the team at the start of the internship.
Toolchain & Environment
The internship may involve technologies such as:
- C++ and Python
- LLVM compiler infrastructure
- Graphics and compute APIs: Vulkan, OpenCL, DirectX
- Shader/kernel languages and IRs: GLSL, HLSL, SPIR-V, OpenCL C
- GPU performance profiling and debugging tools
- Linux/Windows development environment, Git and CI infrastructure
Skills / Experience
Essential:
- Good programming skills in C++, plus familiarity with Python or a similar scripting language.
- Understanding of compiler fundamentals, such as parsing, intermediate representations, data-flow analysis, optimisation passes and code generation, gained through coursework or projects.
- Basic understanding of computer architecture: pipelines, memory hierarchy, caches and instruction sets.
- Strong analytical, debugging and problem-solving skills.
- Interest in performance and in how software maps onto hardware.
Desirable but not essential:
- Experience with LLVM, GCC or another production or research compiler framework.
- Knowledge of GPU architecture and the GPU programming model (SIMT, warps/waves, divergence, occupancy).
- Experience with graphics or compute APIs (Vulkan, OpenGL, OpenCL, CUDA, DirectX) or shader programming.
- Familiarity with SPIR-V or other shader intermediate representations.
- Exposure to performance profiling, benchmarking or low-level optimisation.
- Contributions to open-source compiler, graphics or ML projects.
Experience in all of these areas is not required. We value curiosity, a willingness to learn, and the ability to work through open-ended technical problems.
Responsibilities
This is a fixed-term placement of 3 months. You will be supported by experienced GPU compiler engineers and will contribute to active GPU compiler development.
Typical activities may include:
- Implementing, testing and benchmarking compiler features or optimisations within the GPU compiler toolchain.
- Analysing generated GPU code and runtime performance data to understand the impact of compiler transformations.
- Writing and running graphics and compute tests to assess functionality and performance and to identify issues.
- Developing scripts and tools for test automation, data processing and performance visualisation.
- Collaborating with GPU architecture, driver and validation teams to understand hardware behaviour and customer workloads.
- Documenting designs, experiments, results and recommendations so that the wider engineering team can reuse the work.
Education Requirements
Currently studying towards a Bachelor's, Master's or PhD degree in Computer Science, Computer Engineering, Electrical/Electronic Engineering, Mathematics or a closely related field.
Students with a particular interest in compilers, GPU architecture, graphics, high-performance computing or programming languages are encouraged to apply.
What You Will Gain
- Hands-on experience developing a production GPU compiler used across Qualcomm's product portfolio.
- Exposure to GPU architecture, shader and kernel compilation, code generation and quantitative performance analysis.
- The opportunity to deliver a focused, meaningful project as part of a newly established team in Cambridge.
- Mentorship from experienced compiler engineers and collaboration with architecture, driver and validation specialists.
*References to a particular number of years experience are for indicative purposes only. Applications from candidates with equivalent experience will be considered, provided that the candidate can demonstrate an ability to fulfill the principal duties of the role and possesses the required competencies.
Applicants: Qualcomm is an equal opportunity employer. If you are an individual with a disability and need an accommodation during the application/hiring process, rest assured that Qualcomm is committed to providing an accessible process. You may e-mail [email protected] or call Qualcomm's toll-free number found here. Upon request, Qualcomm will provide reasonable accommodations to support individuals with disabilities to be able participate in the hiring process. Qualcomm is also committed to making our workplace accessible for individuals with disabilities. (Keep in mind that this email address is used to provide reasonable accommodations for individuals with disabilities. We will not respond here to requests for updates on applications or resume inquiries).
Qualcomm expects its employees to abide by all applicable policies and procedures, including but not limited to security and other requirements regarding protection of Company confidential information and other confidential and/or proprietary information, to the extent those requirements are permissible under applicable law.
To all Staffing and Recruiting Agencies: Our Careers Site is only for individuals seeking a job at Qualcomm. Staffing and recruiting agencies and individuals being represented by an agency are not authorized to use this site or to submit profiles, applications or resumes, and any such submissions will be considered unsolicited. Qualcomm does not accept unsolicited resumes or applications from agencies. Please do not forward resumes to our jobs alias, Qualcomm employees or any other company location. Qualcomm is not responsible for any fees related to unsolicited resumes/applications.
If you would like more information about this role, please contact Qualcomm Careers.