Member of Technical Staff GPU Performance Engineer
Liquid AIVisit Liquid AI website
Liquid AI is an efficiency-first foundation-model company building device-native Liquid Foundation Models (LFMs) and tools to customize and deploy them.
Cambridge, Massachusetts, United States
Funding history
About Liquid AI
An MIT CSAIL spinout, Liquid AI develops general-purpose AI models focused on efficient deployment across CPUs, GPUs, NPUs, edge devices, and cloud or on-premises environments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will write and integrate custom GPU kernels, profile training and inference workflows, and remove performance bottlenecks. You will build correctness and numerical tests, maintain benchmark guardrails, and turn research ideas into reliable production speedups.
Requirements
- Experience authoring custom CUDA kernels
- Understanding of GPU architecture and performance, including memory hierarchy, warps, shared memory, register pressure, bandwidth, and compute limits
- Proficiency with Nsight Systems or Nsight Compute and performance methodology
- Strong C and C++ skills
Responsibilities
- Write high-performance GPU kernels
- Integrate kernels into PyTorch pipelines
- Profile and optimize training and inference workflows
- Build correctness tests and numerical checks
- Build and maintain performance benchmarks and regression guardrails
- Turn research ideas into shipped performance improvements
Benefits
- Equity
- Medical, dental, and vision premiums fully paid for employees and dependents
- 401(k) matching up to 4% of base pay
- Unlimited PTO
- Company-wide Refill Days