Skymizer is developing a software stack for deploying AI models at various types of AI system-on-chips, from high-performance cloud to cost-effective edge devices.

As a senior software engineer of AI compiler, you will help develop a compiler and/or related tools to transform any AI models into hardware instructions that can efficiently run on a target machine.

Your contribution is important for enabling those exciting deep neural network models really working in the daily life. Without compiler, handcrafting instructions is not scalable.

This job is also challenging, though. Compiling a deep neural network model is, in many aspects, different from compiling a programming language. However, the state-of-the-art practice of conventional compilers is still worth a reference. So, you are expected to be familiar with LLVM or GCC. Based on the conventional wisdom, you should suggest a best practice for the neural network case.

Just like LLVM/GCC, we heavily use C++. You should be familar with modern C++ techniques, and be able to program in a logical, reusable, and timely fashion.

Responsibilities

• Develop software architecture of AI compiler.
• Deliver high-quality implementation on schedule.
• Present the techniques in public.

Minimum qualifications

• Experience with C++ programming.
• Experience with MLIR, LLVM or GCC.
• Bachelor’s or above in Computer Science or related technical discipline.

Preferred qualifications

• Knowledge of deep neural network model.
• Communication in English.
• 8+ years of professional software development experience.