Kernel Engineer (Internship and Full-time)
Tilde ResearchAdded 6d ago
Save this job and browse the whole board.
No credit card needed
AI analysis
ProJev · full postingQuick summaryby newgrad.ai
What you'll do
- Design, implement, and optimize high-performance GPU kernels for training and inference
- Collaborate with ML researchers to co-design performance-aware models and infrastructure
- Contribute to system-wide efficiency improvements beyond kernel-level optimizations
What they're looking for
- Deep learning or related research experience with demonstrated ML kernel capabilities
- Strong proficiency in PyTorch, Triton/TK/TileLang; basic CUDA and GPU architecture knowledge
- Clear communication skills, strong algorithmic thinking, and quick learning ability
- Portfolio evidence: open source contributions, technical writing, or hardware-aligned algorithm work
Tilde Research is a moonshot AI lab advancing mechanistic interpretability, new architectures, and pretraining science. We build foundational understanding of models to advance the frontier of intelligence.
About the role
Apply on Tilde Research's site.
Apply nowListing wrong or expired, or you're the employer and want it removed? Let us know.
