ML Inference Engineer - AWS Neuron & GenAI

Annapurna Labs (U.S.) Inc. in Cupertino, CA, seeks engineers to design and optimize ML models for AWS Neuron on Inferentia and Trainium accelerators, bridging software and hardware for high-performance inference and training. You will work across frameworks, kernels and compilers, implement high-performance ML kernels, profile performance, and collaborate with customers to enable their models on AWS accelerators, in a fast-paced startup‑like culture.