Description
Tether is hiring an AI Researcher to advance model compression and efficient deployment for multimodal AI systems, including large language models and vision-language models. The role focuses on quantization, knowledge distillation, pruning, mixed-precision techniques, and production inference optimization for low-memory, low-latency edge devices. Responsibilities include developing compression pipelines, measuring performance and fidelity, publishing research, and documenting methodologies. The posting requires a degree in computer science or a related field, experience with PyTorch and model compression techniques, and familiarity with neural network architectures; a PhD in a relevant field and C++ knowledge are preferred.
