Senior Compiler Engineer (GPU)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Senior Compiler Engineer (GPU): Develop, enhance, and optimize compiler software for 's GPU programming models including OpenCL, SYCL, and OpenMP with an accent on IR interfaces, optimization algorithms, and code generation. Focus on collaborating with hardware architects to define new GPU features, analyzing workloads for bottlenecks, and driving performance gains for AI and high-performance computing.
Location: US, California, Santa Clara (Hybrid work model - split time on-site and off-site)
Salary: $149,600–$284,580 USD
Company
Leader in AI technologies, foundational software stacks, and GPU IP for client and data center markets.
What you will do
- Develop, test, debug, and maintain compilers for GPU programming models like OpenCL, SYCL, OpenMP.
- Design IR interfaces between front-ends and Graphics Compiler.
- Implement optimization algorithms to improve code performance and efficiency.
- Collaborate with GPU hardware architects on microarchitecture features and ISA.
- Analyze generated code, identify inefficiencies, and propose optimizations or hardware changes.
- Evaluate workloads, refine compilation for advanced use cases, and author technical documents.
Requirements
- Bachelor's in Computer Science, Computer Engineering, Software Engineering, Electrical Engineering, or STEM field
- 5+ years in C/C++ programming, data structures, OOP
- 2+ years in compiler architecture, phases, code optimizations
- Experience with development tools (GitHub, Jira, CMake).
- Experience in scripting (Python, Shell).
- Experience developing on Linux and Windows.
Nice to have
- Post-graduate degree in relevant field.
- LLVM/MLIR expertise.
- GPU programming model knowledge.
- Compiler optimization experience.
- Performance tuning skills.
Culture & Benefits
- Competitive pay, stock bonuses, health, retirement, and vacation benefits.
- Hybrid work model splitting on-site and off-site time.
- Opportunity to impact AI, HPC, and future GPU architectures.
- Collaborative environment with hardware and software teams.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →