Core ML Engineer (Inference) — Full Time

We are looking for a Core ML Engineer to oversee and validate our path to world-class inference software. You will be responsible for ensuring we make the right technical decisions as we build high-performance inference pipelines and optimize model execution across heterogeneous hardware.

The ideal candidate has deep experience with ML frameworks, GPU programming (CUDA/ROCm), and a passion for squeezing every last drop of performance from silicon. You’ll guide our technical direction, validate architectural choices, and work closely with our systems team to build infrastructure that serves millions of inference requests with minimal latency.