1 day ago
Bengaluru, IndiaSenior
Responsibilities
- Conduct competitive analysis of GPU compiler performance and architectures from AMD, Intel, Nvidia, and ARM.
- Profile and characterize games, HPC workloads, AI applications, and other GPU benchmarks to identify performance bottlenecks.
- Develop, optimize, debug, and improve LLVM-based GPU compilers and compiler algorithms.
- Apply AI and machine learning methods to compiler optimization, performance analysis, and performance modeling.
- Evaluate AI-based graphics techniques for rendering, upscaling, denoising, and other visual improvements.
- Propose compiler, GPU architecture, and application changes to improve Qualcomm GPU performance.
- Develop benchmarking and performance modeling tools and support optimization for Snapdragon Elite Windows on Arm.
- Summarize comparative profiling results and present findings to customers and internal teams.
Requirements
- Bachelor's degree in Engineering, Information Systems, Computer Science, or a related field plus 4+ years of Systems Engineering or related experience; alternatively, a master's degree plus 3+ years or a PhD plus 2+ years.
- Experience in compiler development and AI-based optimization techniques.
- Hands-on experience with LLVM compiler infrastructure, LLVM IR, pass development, and LLVM-based GPU compilers.
- Understanding of GPU and computer architecture, memory, data layout, and performance tradeoffs.
- Proficiency in C/C++ and scripting languages such as Python, with experience using machine learning frameworks.
- Experience or familiarity with graphics programming, OpenCL, CUDA, performance profiling tools, hardware performance counters, and parallel application benchmarking.
- Experience with scikit-learn, TensorFlow, or similar machine learning or deep learning tools is a plus.
- Experience optimizing Windows on Arm platforms and exposure to AI-based graphics techniques are plus qualifications.
- Strong communication, teamwork, reliability, and self-motivation.
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.