обновлено 1 день назад
GPU Software Engineer (CUDA)
100 000 - 175 000$
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/HPC): Designing and optimizing high-performance CUDA kernels, GPU libraries, and distributed workloads for AI training, inference, scientific computing, and high-throughput data processing with an accent on memory hierarchies, multi-GPU execution, and mixed-precision computation. Focus on profiling production GPU systems, building custom operators for ML frameworks, optimizing compiler and accelerator code paths, and mentoring engineers through complex performance challenges.
Location: 100% remote within the United States
Salary: $100,000–$175,000 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 implement high-performance CUDA kernels for AI and high-performance computing workloads.
- Profile and optimize GPU code using Nsight Systems, Nsight Compute, and CUDA profiling tools.
- Tune memory access, occupancy, register usage, shared memory, and broader GPU memory hierarchy utilization.
- Develop optimized libraries, custom operators, and fused kernels for PyTorch, JAX, or Triton.
- Optimize multi-GPU and multi-node workloads using NCCL, RDMA, and high-performance networking.
- Build benchmarks and regression tests, evaluate GPU architectures, document tuning decisions, and mentor engineers.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
- 10+ years of experience in GPU programming and performance engineering.
- Deep expertise in CUDA C/C++, GPU programming models, modern GPU architectures, memory hierarchies, and execution models.
- Production experience profiling and optimizing GPU workloads, with strong C++ and systems programming skills.
- Experience with NCCL, MPI, high-performance interconnects, and integrating custom kernels into machine learning frameworks.
- Strong knowledge of linear algebra and numerical methods, along with effective communication and collaboration skills.
Nice to have
- Experience with Triton, CUTLASS, TensorRT, FasterTransformer, or vLLM internals.
- Exposure to LLVM or MLIR compiler infrastructure.
- Open-source contributions to GPU or machine learning performance libraries.
- Experience with large-scale distributed training infrastructure.
Culture & Benefits
- Full-time direct W-2 employment.
- Remote work within the United States.
- Collaboration with product, design, engineering, operations, and business stakeholders.
- Opportunities for career growth, technical mentorship, and cross-functional work.
- U.S. citizens, Green Card holders, EAD holders, and H-1B transfer candidates may apply; new H-1B visa petitions are not sponsored.
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 →
Музыка
Осень
Поддержка