ARTIFICIAL INTELLIGENCE ENGINEER
Description
We are looking for a seasoned AI engineer that wants to join a company developing one of the most advanced AI SoCs. In this role you will be responsible to deliver different AI model families, evaluate the compiler performance and robustness and optimize the compiler to solve potential bottlenecks in the model execution. As an AI engineer, you will define what are the best methodologies to tune and quantize models targeting our hardware.
Responsibilities
- Integrate in our SW ecosystem new models that are key to our customers
- Define what is the default quantization methodology to extract full performance of our HW without losing accuracy
- Tune model architectures to better fit our HW and compiler strengths
- Architect new networks that have an excellent fit in our HW and compiler and can show a competitive advantage
- Employ advanced profiling techniques and optimization strategies to continuously improve the performance of AI software.
Minimum Qualifications
- +2 years of experience in ML frameworks like Pytorch/Tensorflow
- Deep knowledge of different AI architectures
- C++ and Python knowledge or other scripting languages
- Linux distribution knowledge
- BS in Computer Science or a related technical field
- Business fluent English
Desired Qualifications
- Knowledge of different quantization schemes
- Model conversion between different framework formats
- Strong knowledge of C++ coding best practices, writing robust leak/crash free code