Senior Vision Systems Engineer
Do uzgodnienia
Wymagania
- C++
- OpenCV
- PyTorch
- TensorFlow
- ONNX
Opis stanowiska
- hands-on technical leader responsible for designing, optimizing, and productizing high-performance computer vision and AI pipelines for consumer devices. This role ensures real-time performance, power efficiency, and production robustness across embedded platforms.
- Design and implement advanced computer vision and image processing pipelines optimized for real-time consumer devices.
- Collaborate with ISP, sensor, and tuning teams to optimize image quality for downstream AI and UX performance.
- Develop and deploy ML models for visual recognition, enhancement, tracking, or scene understanding.
- Optimize ML models for edge deployment (quantization, pruning, distillation, hardware-aware tuning).
- Implement performance-critical algorithms in modern C++ for embedded platforms.
- Optimize for latency, power consumption, memory footprint, and thermal constraints.
- Integrate inference engines (TFLite, TensorRT, ONNX Runtime, etc.) on target SoCs.
- Work closely with Android/Linux platform teams to integrate camera and AI pipelines.
- Define and track KPIs: FPS, power usage, memory, startup time, and accuracy.
- Profile and optimize performance across CPU/GPU/NPU/DSP.
- Drive debugging of complex system-level issues in production builds.
- Ensure robust unit testing and contribute to automated validation pipelines.
- Mentor engineers and review architecture/design proposals.
- Support product bring-up and mass production readiness.
- Design and implement advanced computer vision and image processing pipelines optimized for real-time consumer devices.
- Collaborate with ISP, sensor, and tuning teams to optimize image quality for downstream AI and UX performance.
- Develop and deploy ML models for visual recognition, enhancement, tracking, or scene understanding.
- Optimize ML models for edge deployment (quantization, pruning, distillation, hardware-aware tuning).
- Implement performance-critical algorithms in modern C++ for embedded platforms.
- Optimize for latency, power consumption, memory footprint, and thermal constraints.
- Integrate inference engines (TFLite, TensorRT, ONNX Runtime, etc.) on target SoCs.
- Work closely with Android/Linux platform teams to integrate camera and AI pipelines.
- Define and track KPIs: FPS, power usage, memory, startup time, and accuracy.
- Profile and optimize performance across CPU/GPU/NPU/DSP.
- Drive debugging of complex system-level issues in production builds.
- Ensure robust unit testing and contribute to automated validation pipelines.
- Mentor engineers and review architecture/design proposals.
- Support product bring-up and mass production readiness.
🔍 Dekoder Ogłoszenia
🔴
hands-on technical leader responsible for designing, optimizing, and productizing high-performance computer vision and AI pipelines for consumer devices.
Oczekuje się, że będziesz nie tylko projektować i optymalizować, ale także aktywnie kodować i rozwiązywać problemy na poziomie produkcyjnym, często w ograniczonych zasobach.
🔴
Mentor engineers and review architecture/design proposals.
Oprócz zadań technicznych, będziesz odpowiedzialny za nadzór nad młodszymi inżynierami i ocenę ich pracy, co może oznaczać dodatkowe obowiązki zarządcze.
🔴
Drive debugging of complex system-level issues in production builds.
Przygotuj się na rozwiązywanie trudnych problemów, które pojawiają się w gotowych produktach, co może być czasochłonne i frustrujące.
🔴
Support product bring-up and mass production readiness.
Twoja praca będzie ściśle powiązana z cyklem produkcyjnym, co może oznaczać pracę pod presją czasu i konieczność szybkiego reagowania na problemy produkcyjne.
🟡
Optimize ML models for edge deployment (quantization, pruning, distillation, hardware-aware tuning).
Wymaga głębokiej wiedzy i praktycznego doświadczenia w zakresie optymalizacji modeli uczenia maszynowego pod kątem bardzo ograniczonych zasobów sprzętowych, co jest specyficzną i często trudną dziedziną.