GPU Software Engineer (CUDA)

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 profiling tools.
• Tune memory access, occupancy, register usage, shared memory, HBM, and L2 utilization.
• Develop optimized libraries, custom operators, and fused kernels for PyTorch, JAX, or 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

• Must be based in the United States for this remote position.
• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
• Six or more years of GPU programming and performance engineering experience.
• Deep expertise in CUDA C/C++, GPU architectures, memory hierarchies, and execution models.
• Production experience profiling and optimizing GPU workloads, including familiarity with NCCL, MPI, and high-performance interconnects.
• Experience integrating custom kernels into ML frameworks, with strong systems programming, linear algebra, numerical methods, 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 ML 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, business, research, and ML teams.
• Opportunities for career growth, technical leadership, code review, design review, and mentorship.
• New H-1B visa petitions are not sponsored; U.S. citizens, green card holders, EAD holders, and H-1B transfer candidates may apply.