Job Description
We are bringing the next generation of AI enabled user interaction to Mercedes-Benz cars using deep learning. As a machine learning platform engineer, you will develop platform software related components for one of the most innovative, cutting-edge and technologically advanced product.
You will be responsible for compressing & quantising neural networks, develop tools and methodologies to perform platform specific quantisation with minimal loss in accuracy.
Responsibilities
- Develop new ideas for machine learning within Pytorch
- Optimize existing implementations within Pytorch
- Research & implement distributed learning strategies.
- Enhance multi-gpu and multi-node capabilities in Pytorch
- Interface with research team to understand neural network algorithms.
- Research and develop compression strategies for the target devices.
- Document work artifacts and ensure alignment with internal development processes.
Desired Skills and Experience
- Bachelor’s degree in Engineering.
- Minimum 4 years of relevant work experience, including hands-on development experience in C/C++, CUDA, Pytorch
- Expert at python programming
- Experience working on Unix based environment and/or embedded devices.
- Good understanding of Linux OS
- Experience on Shell scripting, Makefile
- Excellent troubleshooting skills to root cause complex issues
- Strong Data structure Knowledge
- Strong Debugging & Bug-fixing skills
- Good Analytical & Problem Solving skills
- Sound Knowledge on Git and similar agile development practices.
- Experience on OpenCL, Machine Learning is plus
- Experience on Software Design, Architecture
- Experience working with V100 GPUs