Senior Inference ML Engineer: Transformers & Vision

Cerebras Systems is seeking a Senior Research Engineer for the Inference ML team to adapt and optimize language and vision models for our Cerebras hardware. You will collaborate with researchers and engineers to design, prototype, validate, and optimize end-to-end inference pipelines.

Responsibilities include advancing speculative decoding, pruning, compression, and sparse attention, training models to convergence, and profiling performance to deliver low-latency inference at scale.