Edge AI Inference Engineer: Kernel & Speed Optimization

Tether Operations Limited is seeking a specialized candidate for a fully remote position focusing on the design and deployment of state-of-the-art model serving architectures. The ideal applicant should have a PhD in NLP or Machine Learning, with a solid AI R&D track record and expertise in GPU kernels.

The role includes optimizing and integrating frameworks for low-resource devices, ensuring high performance, and diagnosing computational bottlenecks. If you have deep technical knowledge and proven experience in inference optimization, this opportunity is for you.