Job Duties
- Perform analysis of neural network performance: GPU and CPU memory consumption, hardware utilization, latency of neural network and data transfers.
- Compare and analyze hardware solution for neural networks inference: perform integrated analysis of device energy consumption, compare latency of neural network inference on different devices, compare accuracy loss for different optimization techniques.
- Implement and integrate algorithms of efficient neural networks inference on edge devices.
- Deploy neural networks to edge devices.
- Work together with a machine learning development team to develop neural algorithms that meet resource constraints while preserving high quality of predictions and planning.
Job Requirements
- Master’s degree in computer science, engineering or mathematics, or their equivalents.
- At least 4 years of relevant work experience in IT.
- Strong knowledge of such programming languages: C/C++, Python.
- Understanding of data structures and software architecture.
- Experience with the application of machine learning and optimization algorithms.
- Experience with machine learning frameworks: Tensorflow, PyTorch.
- Strong CUDA programming skills.
- Experience with: Docker containers, Git.
- Understanding of how general pipelines of autonomous vehicles work.
- Strong software engineering and development skills.
- Critical thinking and problem-solving skills.
Please note that the office is located in Austin, TX. At this time, the employer is not sponsoring candidates relocation and remote work options are not available.
Your application has been sent. Thank you!
We'll get back to you within a week
