Job Description
Job DescriptionGreetings!
High Performance Computing/AI Platform Engineer
Santa Clara, CA -
5 Days Onsite
Face to face interview after L1 is clear
High Performance Computing/AI Platform Engineer
Must have --CUDA, GPU
Job Summary Seeking an experienced GPU Computing Engineer/AI platform engineer with expertise in CUDA programming, parallel algorithm development, workload scheduling, and performance optimisation. The candidate will develop scalable GPU-accelerated solutions for AI, simulation, scientific computing, and high-performance data processing applications.
Key Responsibilities
Develop and optimise CUDA kernels.
Design parallel processing frameworks for massive datasets.
Implement GPU scheduling and resource allocation mechanisms.
Profile, benchmark, and tune applications for maximum throughput.
Develop multi-GPU and distributed GPU solutions.
Collaborate with AI/ML, systems, and infrastructure teams.
Skills
CUDA C/C
GPU Architecture (NVIDIA)
Parallel Computing
Multithreading
OpenMP, MPI, NCCL
Linux
Python
Performance Engineering
Scheduling Algorithms
Kubernetes (preferred)
Slurm (preferred)
Experience
5 12 years in HPC, GPU Computing, AI Infrastructure, or Performance Engineering.