Intern Assistant Engineer – AI Inference Performance Full-time

Our team has an immediate 12-month internship opening for an Assistant Engineer.

Responsibilities:

• Assist in developing and maintaining performance monitoring tools.
• Support profiling and analyzing inference workloads to identify performance bottlenecks.
• Contribute to applying optimization techniques such as quantization, kernel fusion, and pruning to enhance inference performance under the guidance of senior engineers.
• Help optimize AI workloads across multiple hardware platforms (e.g., GPUs, edge devices).
• Collaborate with senior engineers, research teams, and AI infrastructure teams to integrate optimizations into AI inference pipelines.
• Learn to utilize profiling tools such as TensorBoard, PyTorch Profiler, and NVIDIA Nsight to identify key performance insights.

What you’ll bring to the team:

• Currently pursuing or recently graduated with a Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, AI/ML, or a related field.
• Familiarity with programming languages like Python or C++.
• Basic knowledge of deep learning frameworks (e.g., TensorFlow, PyTorch) and AI inference.
• Strong background in profiling and performance analysis tools.
• Strong analytical and problem-solving skills with an eagerness to learn.