Hello, I'm

Kulin Seth

Engineering Manager at Apple, leading the Server ML Frameworks team. Designed the distributed inference engine for Private Cloud Compute. Previously at VMware and Qualcomm building GPU drivers and graphics systems.

Machine Learning Distributed Inference GPU Programming PyTorch CUDA Graphics Drivers

What I Do

ML Inference & HPC

Leading distributed inference for LLMs and diffusion models on server platforms. Designed the core engine powering Apple Intelligence's Private Cloud Compute.

ML Frameworks

PyTorch MPS backend maintainer. Led GPU backend support for PyTorch, JAX, and TensorFlow. Deep experience with MLIR, Triton, and LLVM.

GPU & Graphics

Building and optimizing GPU drivers and 3D virtualization systems. Deep experience with Metal, CUDA, OpenGL ES, Vulkan, and compute workloads.

Systems Engineering

Hypervisor development, compiler front-ends, GPU architecture simulation, and design space exploration for heterogeneous platforms.