AI Inference Architect: Edge-Optimized Kernels & Fast Serving

Tether.io is seeking a skilled AI model team member to optimize model serving architectures for advanced AI systems. This role involves delivering high throughput and low latency performance across various deployments, particularly in resource-constrained environments.

The ideal candidate will have a strong academic background in Computer Science, preferably a PhD, alongside proven expertise in GPU kernel optimizations and inference techniques. Join us in revolutionizing digital finance.