19 hours ago
Toronto, Canada +4 moreMid Level
H1B sponsor
Responsibilities
- Use NVIDIA Nsight Systems, Nsight Compute, and PyTorch Profiler to investigate GPU utilization, kernel execution, memory bandwidth, and CPU–GPU data movement.
- Identify and optimize bottlenecks across model execution, preprocessing, and inference serving.
- Improve performance through batching, scheduling, memory management, and better GPU utilization.
- Develop or integrate high-performance GPU kernels when existing implementations limit performance.
- Build benchmarks and automated checks to detect performance regressions across representative video workloads.
- Collaborate with AI researchers and infrastructure engineers to bring optimizations into production.
- Measure the effects of changes on latency, throughput, cost, and output quality.
Requirements
- Experience optimizing GPU-based AI workloads or high-performance computing systems.
- Proficiency in Python and experience with PyTorch or a similar machine learning framework.
- Strong understanding or curiosity about GPU hardware, including memory bandwidth, cache behavior, tensor cores, and CPU–GPU data movement.
- Experience using profiling tools to connect hardware behavior to application bottlenecks and validate improvements.
- Ability to turn performance experiments into reliable production changes and communicate tradeoffs clearly.
- Preferred: experience with CUDA, Triton, or C++ GPU programming; optimization of video, image, audio, diffusion, or Transformer models; multi-GPU inference, GPU interconnects, quantization, or large-scale model serving; performance benchmarks or regression-testing infrastructure; and work in a fast-paced technology environment.
Benefits
- Competitive salary and benefits package.
- Dynamic and inclusive work environment.
- Professional growth and advancement opportunities.
- Collaborative culture valuing innovation and creativity.
- Access to the latest technologies and tools.
Categories
About HeyGen
HeyGen builds an AI video platform for businesses and creators to generate videos with avatars, text-to-speech, and translation across languages. Its web-based tools and APIs support use cases like marketing, training, and localization, offered as subscription software with add-ons for enterprise teams. Founded in 2020 and headquartered in Los Angeles, the company is privately held.