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 an AI software engineer, you will help develop compiler, runtime, and related tools to transform any AI models into what can really work on a target machine.

Your contribution is important for enabling those exciting deep neural network models really working in the daily life. Without software stack, hardware alone cannot do anything.

This job is also challenging, though. Compiling a deep neural network model is, in many aspects, different from compiling a programming language. You will deal with many classic compiler problems such as legalization, resource allocation, scheduling, and code emission, but re-implement them for the need of deep neural network models.

We are heavily using C++. You should be familiar with modern C++ techniques, and be able to program in a logical, reusable, and timely fashion.

Responsibility

• 設計與開發『AI 模型部署』的 Framework 與 System
• 開發 Benchmarking 與 Profiling Framework 與 System
• AI 模型相關優化及部署上的優化

Minimum qualifications

• 精通 Python (e.g, metaclass)
• 熟悉 C/C++ 語言
• 熟悉軟體設計原則及設計樣式
• 具獨立研究與開發能力
• 資訊科學系學士以上學歷
• 3年以上工作經驗

Preferred qualifications

• 具有 backend 經驗, e.g. 瞭解 Message Queue, Database, Networking, Pipeline, …etc.
• 瞭解 Deep Learning 基礎知識
• 瞭解 MLOPs 或 ML Pipeline