Staff Python / PyTorch Developer — Frontend Inference Compiler – Dubai

Build and optimize APIs, machine-learning features, and tools that enable state-of-the-art generative AI models to run efficiently on Cerebras custom hardware. Work on high-throughput, low-latency multimodal inference for image, audio, and video, and help scale the serving backend using observability and performance analysis. Lead technical guidance for a team, shape ML ecosystem evolution, and deliver robust automated testing in an agile environment.