Step into a key role as an AI Model Compression Engineer at I Machines, Inc., where you will work on innovative compression techniques for AI models. Engage in optimizing model performance across multiple architectures with hybrid methods.

You will be part of a dynamic software team focused on AI/ML, tasked with developing and executing comprehensive model compression pipelines. This includes utilizing sensitivity analysis and designing quantization strategies tailored for transformer models.

Key Responsibilities: • Own the complete compression pipeline development • Conduct baseline assessments and benchmarking • Implement layerwise sensitivity analysis frameworks • Design and apply quantization strategies effectively • Integrate pruning techniques and hybrid methods to optimize models

Requirements: • Bachelor’s degree in related engineering or science field • Minimum 1 year experience with TensorFlow, JAX, or similar • In-depth knowledge of quantization con...