Job Responsibilities:

• Analyze the performance of neural networks, focusing on GPU and CPU memory usage, hardware utilization, and the latency of neural networks and data transfers.
• Evaluate and compare hardware solutions for neural network inference by conducting comprehensive analyses of device energy consumption, inference latency across devices, and accuracy loss due to optimization techniques.
• Design, implement, and integrate algorithms for efficient neural network inference on edge devices.
• Deploy neural networks to edge computing platforms.
• Collaborate with the machine learning development team to design neural algorithms that meet resource constraints while maintaining high prediction quality and operational planning.

Job Requirements:

• Master’s degree in Computer Science, Engineering, Mathematics, or a related field.
• A minimum of 4 years of relevant experience in the IT sector.
• Proficiency in programming languages such as C/C++ and Python.
• Strong understanding of data structures and software architecture.
• Experience in applying machine learning and optimization algorithms.
• Proficiency in machine learning frameworks like TensorFlow and PyTorch.
• Expertise in CUDA programming.
• Experience with Docker containers and version control systems like Git.
• Familiarity with the general pipeline of autonomous vehicles.
• Strong software engineering skills, critical thinking, and problem-solving abilities.