Looking for something else?
Find a vacancy that works for you. Send us your CV to receive a personalized offer.
Find me a jobWe are seeking a Senior HPC & Distributed CUDA Engineer to join a team working in the upstream domain, focusing on subsurface evaluation and performance-critical scientific computing applications across diverse GPU systems.
Responsibilities
- Optimize CUDA kernels and applications for scientific and engineering workloads
- Improve performance of RTM/FWI seismic imaging workloads
- Tune performance across consumer and data-center GPU platforms
- Implement distributed and multi-GPU computing solutions using MPI, NCCL, and NVSHMEM
- Apply modern CUDA and GPU architecture capabilities to enhance kernel and application performance
- Analyze performance at CUDA kernel, PTX, hardware, and multi-GPU communication levels
- Develop performance-critical software components in C++ and Python
- Profile GPU workloads and identify computational bottlenecks
- Work with large computational workloads where scalability and performance are critical
Requirements
- 5+ years of experience in CUDA kernel and application optimization
- Expertise in CUDA programming, PTX, GPU execution model, memory hierarchy, and NVIDIA GPU architecture
- Experience in distributed and multi-GPU computing using MPI, NCCL, and NVSHMEM
- Proficiency in C++ and Python development
- Background in GPU profiling, performance analysis, and identification of computational bottlenecks
- Skills in optimizing performance for both consumer and data-center GPU platforms
- Familiarity with RTM/FWI seismic imaging workloads
- Proficiency in English at a B2+ level
