Remote GPU Kernel & Inference Engineer (CUDA/Triton)

Anyone Ai Inc.; Santa Fe Capital; À distance; ARS 137 078 000 - 228 464 000; Plein temps

Résumé du poste

Tether is seeking an AI Research Engineer (Kernel & Inference Optimization) to push the performance of model serving architectures. You will optimize inference pipelines for edge and cloud deployments, targeting low latency and memory efficiency across heterogeneous hardware.

Candidates should have deep experience in kernel optimization, GPU compute, and scalable deployment, plus a track record in NLP/ML research. This is a 100% remote worldwide role with global collaboration.

Description du poste

Tether is seeking an AI Research Engineer (Kernel & Inference Optimization) to push the performance of model serving architectures. You will optimize inference pipelines for edge and cloud deployments, targeting low latency and memory efficiency across heterogeneous hardware.

Candidates should have deep experience in kernel optimization, GPU compute, and scalable deployment, plus a track record in NLP/ML research. This is a 100% remote worldwide role with global collaboration.