PSI in Cambridge, MA seeks a performance engineer to own a workload end-to-end—from application code and data path through the scheduler to GPU kernels. You will optimize training loops, simulations, or served models, with benchmarks left behind.
You will write or tailor kernels in CUDA C++ or Triton, profile with Nsight tools, and focus on multi-node AI training, inference serving at scale, or HPC simulations. You will measure real workloads to guide capacity decisions.
#J-18808-Ljbffr
Our team is growing, and we are hiring a Performance Engineer - End-to-End GPU & AI Scaling in Cambridge, MA, United States.
We aim to respond to suitable candidates as soon as possible.
Full responsibilities and requirements are described in the listing above.
Learn more about the Performance Engineer - End-to-End GPU & AI Scaling role in the description above.