Member of Technical Staff - GPU Performance Engineer

The role

You will design, implement, and optimize custom GPU kernels for novel model architectures. You will work with researchers and engineers to identify performance bottlenecks and improve training, post-training, and inference workloads.

What you will do

• Design, implement, and optimize high-performance GPU kernels.
• Profile training, post-training, and inference workloads to identify bottlenecks.
• Optimize memory access patterns, thread and block configurations, register usage, shared memory, and tensor core utilization.
• Integrate custom kernels into PyTorch pipelines.
• Evaluate numerical precision, correctness, and performance tradeoffs.
• Build and maintain benchmarking infrastructure, correctness tests, and performance regression checks.
• Collaborate with researchers to translate architectural innovations into production-ready GPU implementations.

Required qualifications

• Hands-on experience developing and optimizing custom GPU kernels using CUDA or Triton.
• Strong understanding of GPU architecture, including memory hierarchy, thread execution, warps, shared memory, register pressure, occupancy, and compute versus memory bandwidth limitations.
• Demonstrated ability to reason about GPU performance, identify bottlenecks, and make informed optimization decisions.
• Experience profiling, benchmarking, and debugging GPU workloads using tools such as Nsight Systems, Nsight Compute, or equivalent tooling.
• Strong C++ programming skills and experience working with performance-sensitive code.

Nice to have

• Experience with CUTLASS, tensor cores, or advanced matrix multiplication optimizations.
• Experience integrating custom GPU kernels into PyTorch or other ML frameworks.
• Experience optimizing deep learning workloads across training, post-training, or inference.
• Familiarity with numerical precision tradeoffs, mixed-precision computation, and accumulation strategies.
• Experience developing benchmark harnesses, automated performance tests, or regression detection infrastructure.
• Experience optimizing nonstandard model architectures or translating research implementations into production systems.

Benefits

• Competitive base salary with equity in a unicorn-stage company.
• 100% of medical, dental, and vision premiums paid for employees and dependents.
• 401(k) matching up to 4% of base pay.
• Unlimited PTO.
• Company-wide Refill Days throughout the year.

About the company

Spun out of MIT CSAIL, Liquid AI builds general-purpose AI systems that run efficiently across deployment targets. They partner with enterprises across consumer electronics, automotive, life sciences, and financial services.