NVIDIA is looking to accelerate high-performance databases, ETL, and data analytics applications on modern computer architectures using GPUs, as traditional CPU-based data preprocessing and engineering are becoming a bottleneck for ML and DL applications.
Requirements
- Programming fluency in C/C++ with a deep understanding of algorithms and software design.
- Hands-on experience with low-level parallel programming, e.g. CUDA (preferred), OpenACC, OpenMP, MPI, pthreads, TBB, etc.
- In-depth expertise with CPU/GPU architecture fundamentals, especially memory subsystem.
- Domain expertise in high performance databases, ETL, data analytics and/or vector database.
- Experience optimizing/implementing database operators or query planner, especially for parallel or distributed frameworks (e.g. production database or Spark).
- Experience optimizing vector database index build and/or search.
- Experience profiling and optimizing CUDA kernels.
Responsibilities
- In this role, you will research and develop techniques to GPU-accelerate high performance database, ETL and data analytics applications.
- Work directly with other technical experts in their fields (industry and academia) to perform in-depth analysis and optimization of complex data intensive workloads to ensure the best possible performance of current GPU architectures.
- Influence the design of next-generation hardware architectures, software, and programming models in collaboration with research, hardware, system software, libraries, and tools teams at NVIDIA
Other
- Pursuing or recently completed Masters or PhD in Computer Science, Computer Engineering, or related computationally focused science degree or equivalent experience.
- Good communication and organization skills, with a logical approach to problem solving, and prioritization skills.
- Background with compression, storage systems, networking, and distributed computer architectures.
- If you're creative and autonomous, we want to hear from you.
- Applications for this job will be accepted at least until September 8, 2025.
