Founding Gpu Kernel Engineer
SF Tensor- Location
- Not specified
- Work mode
- On-site
- Type
- full time
- Listed
Applications go directly to SF Tensor. Ramai takes no fee for placement and no money for ranking.
[ About this role ]
Founding GPU Kernel Engineer at SF Tensor. This role involves deep optimization of GPU kernels for ML workloads, profiling at the microarchitectural level, and translating hand-optimization insights into automated compiler passes. The engineer will focus on maximizing FLOPs and understanding hardware limitations.
Skills and focus areas
- gpu kernel optimization
- machine learning workloads
- microarchitectural profiling
- compiler optimization
- performance debugging
- cuda
- gpu architecture
- memory hierarchies
- register pressure
- instruction throughput
- thermal throttling
- driver behavior
Summary written by Ramai from the original posting. Full details and requirements are on SF Tensor’s careers page.
[ More at SF Tensor ]
Infrastructure for AI labs to focus on research.
See all 4 open roles at SF Tensor →[ Similar roles at other startups ]
Browse all open engineering roles →[ Not quite right? ]
Tell the assistant what you’re after — stage, location, stack, visa sponsorship — and it searches every open role for you. A few questions are free, no account needed.