Software Engineer, GPU Performance
HeyGen · Los Angeles, Palo Alto, San Francisco, Toronto, Singapore · Los Angeles · Palo Alto · San Francisco · Toronto
CHECKED 8H AGO
Applied AIonsite
At a glance
Highlights
- Speed up AI video experiences like Avatar IV and Video Translation.
- Optimize model execution and inference to cut latency and GPU cost.
- Build benchmarks that catch regressions across video workloads.
What they offer
- Competitive salary and benefits package
- Dynamic and inclusive work environment
- Opportunities for professional growth and advancement
- Collaborative culture that values innovation and creativity
- Access to the latest technologies and tools
Ideal candidate
A performance-obsessed engineer fascinated by how software uses hardware beneath it. You love profiling, measuring tradeoffs, and turning experiments into faster production AI video.
Requirements
- Experience optimizing GPU-based AI workloads or high-performance computing systems
- Proficiency in Python and experience with PyTorch or similar ML framework
- Curiosity about GPU hardware including memory bandwidth, cache, tensor cores and CPU-GPU data movement
- Experience using profiling tools to link hardware behavior to bottlenecks and validate improvements
- Ability to turn performance experiments into reliable production changes and communicate tradeoffs
Lab profile
About HeyGen
AI platform making visual storytelling accessible through generative avatars and scalable video creation.
What they build
- AI avatar video generator
- Text-to-video studio
- AI voice and translation tools
Known for
- Photorealistic generative avatars
- Scalable video production
- Multilingual lip-sync dubbing
Key facts
- Founded in 2020
- Headquartered in Los Angeles, California
- Raised $60M Series A led by Benchmark