We are seeking an experienced C++ Engineer to lead the efficient deployment of our models on various edge AI hardware platforms, including Raspberry Pi, Qualcomm devices, and mobile phones.
This role is crucial for maintaining, optimizing, and porting models across different platforms.
The ideal candidate is a highly skilled engineer with a strong background in systems knowledge and C / C++ programming. They should be self-motivated, capable of working independently, and driven by a passion for performance optimization.
Experience in mobile development and a deep understanding of cache-aware algorithms will be highly valued.
Key Responsibilities
- Model Deployment : Lead the deployment and maintenance of AI models on edge hardware, ensuring optimal performance.
- Optimization : Optimize models for various hardware platforms, focusing on NPUs and mobile devices.
- Porting : Manage the porting of models to different platforms, enhancing compatibility and performance.
- Maintenance : Continuously update and maintain models to ensure they run efficiently on target hardware.
Required Skills
- Systems Knowledge : Extensive understanding of cache hierarchy, vector instructions, CPU-GPU interactions, and other low-level systems knowledge.
- Programming : Proficiency in C / C++ is essential. Experience with Swift, Java, or Kotlin for iOS / Android development is highly desirable.
- Independence : Ability to work independently and drive projects without supervision
Highly Desired Skills / Traits
- Cache-Aware Algorithms : Proven experience with cache-aware algorithms. This role requires a deep understanding beyond the average knowledge in this area.
- Performance-Driven : A competitive mindset focused on achieving the fastest CPU inference stack. This role suits individuals who see optimization as a competition.
30+ days ago