AI Inference Engine Software Engineer (AI推理引擎软件工程师)
As part of global AI SW team, you will co-work with different engineers from different countries/locations focusing on AI inference engine project for own SoC under heterogonous computing env.
Job description
- Build up high performance inference engine based on private IR to maximize utilization of our own SoC under heterogonous computing env.
- Performance various optimization on different IR levels.
- Buildup PTQ tool for models.
- Co-work with algorithm engineer to deploy SOTA edge computing models on our SoC.
Job Qualification
- Master’s degrees or top bachelors on EE/Computer Science or related majors.
- Solid programming skills on modern C++.
- Rich experience on multi-threading programming.
- Rich experience on inference and performance optimization.
- Background on CV DNN models is a plus.
- Experience on SIMD and ASM is a plus.
- Experience on numerical lib implementation is a plus.
- Edge computing experience is a plus.