Research Scientist / Engineer - Performance Optimization
Company revealed to Pro
- Location
- Remote (United States)
- Pay
- $195K to $395K a year
- Employment
- Full-time
Employer posted Oct 8 · Added to VDJ Oct 9 · Last checked today
AI company. This company doesn't make vertical drama. We list the role because the skills carry straight over to vertical work.
About the role
You'll write the kernels and operations that get the most out of the hardware. Pro members see the company and apply now. It opens to everyone on November 7.
What they're looking for
- Expert-level Triton/CUDA programming and GPU optimization.
- Strong PyTorch skills, including kernel development and custom operations.
- Proficiency with profiling tools (NVIDIA Nsight, torch profiler, custom tooling).
- Deep understanding of transformer architectures and attention mechanisms.
Nice to have
- Experience with compilers and exporters (torch.compile, TensorRT, ONNX, XLA).
- Experience optimizing inference workloads for latency and throughput.
- Triton compiler and kernel fusion techniques.
- Knowledge of warp-level intrinsics and advanced CUDA optimization.
We found this on the studio's own hiring page.
Pro members see the company and the apply link, and apply first. It opens to everyone after 30 days.
Get Pro for $10 a weekSign up free to open 3 fresh jobs a week, company and apply link included.
Fresh role: Pro members see the company and apply for the first 30 days. More Tech & business jobs →