Description
We are seeking a self-motivated PhD Intern to drive the adoption of AI/ML functions in the Phy and Mac layers of our Aerial SW at NVIDIA.
As a member of Aerial RAN team working on AI Native stacks, you will contribute to:
- Developing and optimizing AI/ML modules for functional blocks in wireless signal processing
- Conducting literature surveys to understand prior art on AI/ML for RAN
- Analyzing and identifying suitable ML architectures for RAN functions
- Collaborating with multi-functional teams to optimize OTA performance and compute complexity
- Benchmarking OTA performance improvements with AI models and compute needs on different platforms
- Iteratively training, testing, and modifying model architectures for performance improvements
Requirements:
- Full-time PhD student researching AI and Wireless domains
- Understanding of wireless Layer1/Layer2 functions and algorithm aspects
- Excellent grasp of AI and ML concepts, techniques, and latest developments
- Deep understanding of Transformers, CNNs, and other ML Architectures
- Hands-on experience with simulating signal processing algorithms in Matlab and Python
- Programming skills in C/C++
Preferred qualifications:
- Knowledge of CPU, DSP, or GPU architecture
- Experience with programming latency-sensitive, real-time, multi-threaded applications
- Familiarity with CUDA programming and NVIDIA GPU Architectures