GPU Performance Engineer: Accelerate AI Video Pipelines

HeyGen; Los Angeles, Palo Alto, San Francisco (CA, CA, CA); On-site; USD 130,000 - 170,000; Full time

Benefits offered by this job

Competitive salary

Dynamic work environment

Growth opportunities

Collaborative culture

Access to latest tools

Job summary

HeyGen is seeking a Software Engineer focused on GPU performance to accelerate AI video applications and related workloads. You will work across model execution, inference infrastructure, and profiling to reduce latency and cost while increasing throughput.

Ideal candidates will have a strong background in GPU hardware, profiling, and Python-based ML frameworks, with experience in delivering production-grade performance improvements at scale.

Qualifications

• Experience optimizing GPU-based AI workloads or high-performance computing systems.
• Proficiency in Python and PyTorch or a similar ML framework.
• Strong 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-level bottlenecks and validate improvements.
• Ability to turn performance experiments into reliable production changes and communicate tradeoffs clearly.

Responsibilities

• Use profiling tools to investigate GPU utilization, kernel execution, memory bandwidth, and CPU–GPU data movement.
• Identify bottlenecks across model execution, preprocessing, and inference serving, then measure the impact of each optimization.
• 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 that catch performance regressions across representative video workloads.
• Collaborate with AI researchers and infrastructure engineers to bring optimizations into production.
• Measure the effect of changes on latency, throughput, cost, and output quality.

Skills

GPU optimization

Python

PyTorch

Profiling

Latency reduction

Performance tuning

Education

B.S. in CS/EE

Tools

CUDA

Triton

C++

Job description

HeyGen is seeking a Software Engineer focused on GPU performance to accelerate AI video applications and related workloads. You will work across model execution, inference infrastructure, and profiling to reduce latency and cost while increasing throughput.

Ideal candidates will have a strong background in GPU hardware, profiling, and Python-based ML frameworks, with experience in delivering production-grade performance improvements at scale.