About this role
Research Scientist / Engineer - Efficient Modeling at Rhoda AI. Location: Palo Alto, California, United States. Role: research compression, design architectures, profile models Requirements: Experience with model compression, quantization, pruning; PyTorch; transformers; hardware-aware optimization. Category: Research and Development (R&D) Seniority: Mid Level Tools: PyTorch, CUDA, TensorRT, Transformers Commitment: Full Time Workplace: Onsite Languages: English