обновлено 52 минуты назад
GPU Software Engineer (CUDA)
80 000 - 107 000$
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
GPU Software Engineer (CUDA) (AI and High-Performance Computing): Designing and optimizing compute-intensive GPU workloads for AI training, inference, scientific computing, and high-throughput data processing with an accent on CUDA programming, GPU architecture, and production performance engineering. Focus on profiling workloads, integrating custom kernels into ML frameworks, optimizing distributed GPU systems, and delivering reliable C++ software for modern accelerator hardware.
Location: 100% remote within the United States
Salary: $80,000–$107,000 annually
Company
is a technology consulting and software development company delivering cloud, AI, data, and enterprise solutions across the United States.
What you will do
- Design and optimize compute-intensive workloads for modern GPU and accelerator platforms.
- Improve performance for AI training, inference, scientific computing, and high-throughput data processing.
- Profile production GPU workloads and deliver measurable performance improvements.
- Integrate custom kernels into machine learning frameworks and work with distributed computing technologies.
- Translate ambiguous requirements into production-ready solutions with cross-functional partners.
- Contribute through code reviews, design reviews, technical mentorship, and collaboration with research and engineering teams.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
- At least 6 years of experience in GPU programming and performance engineering; the posting states 7+ years of overall experience.
- Deep expertise in CUDA C/C++, GPU programming models, modern GPU architectures, memory hierarchies, and execution models.
- Hands-on experience profiling and optimizing GPU workloads in production, with strong C++ and systems programming skills.
- Familiarity with NCCL, MPI, high-performance interconnects, custom ML kernels, linear algebra, and numerical methods.
- Applicants must be authorized to work in the United States; new H-1B visa petitions cannot be sponsored.
Nice to have
- Experience with Triton, CUTLASS, or other GPU kernel authoring frameworks.
- Familiarity with TensorRT, FasterTransformer, or vLLM internals.
- Exposure to LLVM or MLIR compiler infrastructure.
- Open-source contributions to GPU or ML performance libraries.
- Experience with large-scale distributed training infrastructure.
Culture & Benefits
- Full-time direct W-2 employment.
- Opportunity to collaborate with product, design, engineering, operations, business, and research stakeholders.
- Established organization with opportunities for career growth.
- Equal employment opportunity and a workplace free from harassment and discrimination.
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 →