Parallel Computing Engineer

Job Summary

Bright Vision Technologies is seeking an experienced Parallel Computing Engineer with expertise in CUDA, GPU programming, and High-Performance Computing (HPC) to optimize AI, machine learning, and scientific computing workloads.

Key Responsibilities

• Design and optimize high-performance CUDA kernels for AI and HPC workloads
• Profile and tune GPU applications using Nsight Systems, Nsight Compute, and CUDA tools
• Optimize memory usage, multi-GPU performance, and distributed training with NCCL and MPID
• Develop custom operators and optimized kernels for PyTorch, JAX, or Triton
• Improve training and inference performance for large-scale ML workloads
• Build benchmarks, automate performance testing, and document optimization best practices
• Collaborate with ML and engineering teams to deliver scalable GPU solutions

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related field
• 6+ years of experience in GPU programming and performance optimization
• Strong expertise in CUDA C/C++, GPU architectures, and parallel programming
• Experience with NCCL, MPI, and high-performance networking
• Hands-on experience integrating custom GPU kernels into ML frameworks
• Strong C++ programming, debugging, and analytical skills

Preferred Qualifications

• Experience with Triton, CUTLASS, TensorRT, FasterTransformer, or vLLM
• Knowledge of LLVM/MLIR or compiler technologies
• Experience with large-scale distributed AI training and open-source GPU libraries