Member of Technical Staff - GPU Performance Engineer
Liquid AI · San Francisco · Remote · Boston
CHECKED 22H AGO
Frontier labremote
At a glance
Highlights
- Ship custom kernels that speed up novel model architectures in real pipelines.
- Turn research ideas into production code with measurable throughput gains.
- Own performance guardrails that catch regressions before they reach production.
What they offer
- Equity in a unicorn-stage company
- 100% medical, dental, and vision premiums for employees and dependents
- 401(k) matching up to 4% of base pay
- Unlimited PTO plus company-wide Refill Days
Ideal candidate
Profiler-driven performance engineer who loves memory hierarchies and low-level optimization. You thrive owning ambiguous bottlenecks end-to-end and turning research ideas into robust, shipped speedups.
Requirements
- Authored custom CUDA kernels beyond cuDNN/cuBLAS wrappers
- Strong understanding of GPU architecture and performance fundamentals
- Proficiency with Nsight Systems/Compute profiling and performance methodology
- Strong C/C++ skills
Lab profile
About Liquid AI
MIT CSAIL spinout building efficient general-purpose AI for cloud to edge.
What they build
- Liquid Foundation Models
- LFM2.5-Audio
Known for
- Efficiency-first foundation models
- Data center to on-device deployment
- Low latency with minimal memory usage
- Liquid Neural Networks architecture
Key facts
- Spun out of MIT CSAIL