AI Performance Engineer

Description

We are seeking an experienced AI Performance Engineer to join our team and drive optimization across hardware platforms and machine learning frameworks. The role involves profiling and enhancing AI workload performance, identifying benchmarks for performance analysis, and staying informed about industry trends in AI algorithms and models. You will collaborate with software and firmware teams to troubleshoot complex heterogeneous computing systems, ensuring efficiency and achieving application performance goals. As a key contributor, you will play an essential role in advancing our AI infrastructure and capabilities.

Requirements

1. Minimum of 5 years of experience in C++ and Python programming.

2. Strong understanding of CPU, GPU, and custom ASICs (NPU, TPU, etc.) architectures, along with low-level optimization techniques.

3. Demonstrated expertise with deep learning frameworks like PyTorch or TensorFlow and familiarity with deep learning models.

4. Proven experience in the training and deployment of ML models.

5. Background in distributed systems development, parallel programs, or distributed ML workloads.

6. Knowledge of software development best practices, including testing, profiling, debugging, documentation, version control, and issue tracking.

Desirable

1. Familiarity with emerging AI trends and the latest advancements in AI technology.

2. Experience contributing to open-source AI projects or technologies.

3. Proficiency in tuning and optimizing AI hardware accelerators or custom chips.

Candidate Applications :

⚠️

Applications for this role are closed!

Thank you for visiting!