Vision Systems Architect
Do uzgodnienia
Wymagania
- C++
- Python
- TensorFlow
- PyTorch
- Docker
Opis stanowiska
- Owns the end-to-end vision and AI architecture for consumer devices. Defines scalable, power-efficient, and production-ready imaging and perception systems across product lines. Drives technical direction across sensor, ISP, CV, ML, and platform integration.
- Define and own end-to-end vision system architecture (sensor → ISP → CV/ML → application layer).
- Translate product and UX requirements into scalable technical solutions.
- Define image quality strategy aligned with AI and user experience goals.
- Architect reusable, modular CV/ML frameworks across multiple product SKUs.
- Drive system-level trade-offs across performance, power, cost, and thermal limits.
- Define AI model lifecycle strategy from training to OTA deployment.
- Architect heterogeneous compute utilization (CPU/GPU/NPU/DSP).
- Define system KPIs: latency, FPS, power, memory, boot time, and robustness.
- Lead technology selection for inference engines, frameworks, and hardware platforms.
- Guide SoC bring-up and performance validation for vision pipelines.
- Establish coding standards, modularization strategy, and long-term maintainability.
- Identify technical risks early and define mitigation strategies.
- Collaborate with hardware, ISP, Android/Linux platform, and product teams.
- Mentor senior engineers and provide architectural governance.
- Contribute to long-term vision/AI roadmap across product generations.
- Define and own end-to-end vision system architecture (sensor → ISP → CV/ML → application layer).
- Translate product and UX requirements into scalable technical solutions.
- Define image quality strategy aligned with AI and user experience goals.
- Architect reusable, modular CV/ML frameworks across multiple product SKUs.
- Drive system-level trade-offs across performance, power, cost, and thermal limits.
- Define AI model lifecycle strategy from training to OTA deployment.
- Architect heterogeneous compute utilization (CPU/GPU/NPU/DSP).
- Define system KPIs: latency, FPS, power, memory, boot time, and robustness.
- Lead technology selection for inference engines, frameworks, and hardware platforms.
- Guide SoC bring-up and performance validation for vision pipelines.
- Establish coding standards, modularization strategy, and long-term maintainability.
- Identify technical risks early and define mitigation strategies.
- Collaborate with hardware, ISP, Android/Linux platform, and product teams.
- Mentor senior engineers and provide architectural governance.
- Contribute to long-term vision/AI roadmap across product generations.
🔍 Dekoder Ogłoszenia
🔴
Owns the end-to-end vision and AI architecture for consumer devices.
Będziesz odpowiedzialny za całą architekturę, od koncepcji po wdrożenie, z potencjalnie ograniczonym wsparciem.
🔴
Drives technical direction across sensor, ISP, CV, ML, and platform integration.
Oczekuje się, że będziesz podejmować kluczowe decyzje techniczne w wielu obszarach, nawet jeśli nie jesteś ekspertem w każdym z nich.
🔴
Translate product and UX requirements into scalable technical solutions.
Może oznaczać konieczność radzenia sobie z niejasnymi lub zmieniającymi się wymaganiami biznesowymi.
🔴
Drive system-level trade-offs across performance, power, cost, and thermal limits.
Będziesz musiał podejmować trudne decyzje, które mogą wpływać na jakość lub wydajność produktu ze względu na ograniczenia budżetowe lub techniczne.
🟡
Mentor senior engineers and provide architectural governance.
Oprócz pracy architektonicznej, będziesz miał obowiązki związane z zarządzaniem i rozwojem zespołu.