DNN Model optimization Expert Engineer

Overview

Engineer for neural model optimization and on-device runtime acceleration for GenAI large models (LLM/LVM) on mobile/SoC platforms.

What you'll do

• Design and implement a neural acceleration platform for on-device execution.
• Accelerate networks on one or more processing units.
• Lead design and development of machine learning algorithms for mobile use cases.
• Work with product owners and managers to refine and prioritize the work backlog.
• Identify opportunities to leverage existing platform capabilities.
• Ensure the team produces high-quality code via a predictable process.

What you'll need

• Ph.D in machine learning or a related field (or advanced degree with equivalent industry experience).
• Experience in model optimization using compression/quantization and neural architecture search.
• Knowledge of LLM and LVM for on-device.
• Practical knowledge of machine learning/deep learning.
• Proficiency in Python and Linux.
• Proficiency in C++ and deep/shallow learning frameworks (PyTorch/TensorFlow/AI-Edge).

Details

• Location: Phoenix Building, Bangalore, India.