Назад
Company hidden
обновлено 4 дня назад

GPU Software Engineer (CUDA)

100 000 - 175 000$
Формат работы
remote (только USA)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для 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 custom operators for AI training, inference, scientific computing, and high-throughput data processing with an accent on GPU architecture, memory hierarchies, and multi-GPU systems. Focus on profiling with Nsight tools, compiler-level tensor optimizations, mixed-precision and quantized computation, and preserving performance through benchmarks and regression tests.

Location: 100% remote within the United States

Salary: $100,000–$175,000 annually

Company

hirify.global 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 profilers.
  • Tune memory access, occupancy, register usage, shared memory, and other GPU memory hierarchy parameters.
  • Develop optimized libraries, custom operators, and fused kernels for PyTorch, JAX, and Triton.
  • Optimize multi-GPU and multi-node training with NCCL, RDMA, MPI, and high-performance networking.
  • Build benchmarks and regression tests, evaluate new GPU architectures, document tuning decisions, and mentor engineers.

Requirements

  • Six or more years of experience in GPU programming and performance engineering.
  • Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
  • Deep expertise in CUDA C/C++, GPU programming models, modern GPU architectures, and memory hierarchies.
  • Production experience profiling and optimizing GPU workloads.
  • Experience with NCCL, MPI, high-performance interconnects, and custom kernel integration into ML frameworks.
  • Strong C++ skills, systems programming practices, linear algebra, numerical methods, communication, and collaboration.

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 ML performance libraries.
  • Experience with large-scale distributed training infrastructure.

Culture & Benefits

  • Full-time direct W-2 employment.
  • Collaboration with product, design, engineering, operations, business, research, and ML teams.
  • Opportunities for code review, design review, mentorship, and career growth.
  • Equal employment opportunity workplace.

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 →