Description
Apple is seeking research interns to conduct machine-learning research focused on frontier models, LLM and diffusion-model efficiency, on-device models, speculative decoding, contextual sparsity, quantization, and compression. The intern will work with researchers and engineers through the full research lifecycle, including literature review, novel approach development, code prototyping, large-scale multi-node and multi-GPU experiments, paper writing, and submission. The role requires a doctoral-degree candidate in a relevant field, machine-learning research expertise, relevant conference publications, complex software-engineering skills, and Python fluency; six months of dedication is preferred, with a start no later than March 2026.
