GPU Software Engineer

View full description

Requirements:

• Strong software engineering skills with substantial experience as a practicing software engineer.
• Hands-on experience in distributed compute environments, writing GPU Kernels (e.g. CUDA, PTX, MPX/MLX, IR) and/or implementing GPU-specific optimizations.
• In-depth understanding of deep learning, recent architectural trends, and practical experience with machine learning frameworks like PyTorch, TensorFlow, scikit-learn.

Responsibilities:

• Develop performant GPU kernels and compute infrastructure from the framework level (e.g. PyTorch) down to IR representations.
• Ensure reproducibility in multi-GPU distributed training environments.
• Design novel algorithms focusing on numerical properties and stable compute flows optimized for modern cryptographic systems.