HeyGen
US - California - Los Angeles
View Company Profile /
<< Go Back
Profile GPU workloads and optimize model execution and inference infrastructure to improve latency, throughput, GPU utilization, and cost. Develop or integrate high-performance kernels, build performance benchmarks, and collaborate with research and infrastructure teams to deploy and measure production optimizations.
Requirements: Candidates should have experience optimizing GPU-based AI workloads or high-performance computing systems, proficiency in Python and PyTorch or a similar framework, and familiarity with GPU hardware and profiling tools. They should be able to validate performance improvements, deliver reliable production changes, and communicate tradeoffs; CUDA, Triton, C++, and model-serving experience are preferred.
Key Skills: GPU Performance Optimization, Python, PyTorch, GPU Profiling, NVIDIA Nsight Systems, NVIDIA Nsight Compute, PyTorch Profiler, CUDA, Triton, C++, GPU Kernel Development, Inference Optimization, Performance Benchmarking, Multi-GPU Inference, Quantization, Video Model Optimization
Benefits: Competitive Salary, Professional Growth Opportunities, Inclusive Work Environment, Collaborative Culture, Access to Latest Technologies and Tools
© 2026 engineeringjobs.net, Inc. All Rights Reserved.
Terms of Service | Privacy
Powered by JOBBEX