onsite
Edge AI Engineer - Bright Vision Technologies
AI Engineer
Develop and deploy AI models on edge devices, optimizing performance, latency, and power consumption using Python, C++, TensorFlow, and container orchestration tools.
About the role
Key Responsibilities
- Design, implement, and optimize machine‑learning models for deployment on edge hardware such as IoT gateways, embedded GPUs, and microcontrollers.
- Integrate AI pipelines with container platforms (Docker, Kubernetes) to ensure scalable, reproducible deployments.
- Collaborate with hardware and firmware teams to fine‑tune inference latency, memory footprint, and power usage.
- Convert and compress models using ONNX, TensorRT, or similar frameworks for real‑time execution.
- Monitor model performance in production, troubleshoot issues, and iterate improvements.
Requirements
- Strong programming skills in Python and C++ with experience in AI/ML libraries (TensorFlow, PyTorch, etc.).
- Hands‑on experience deploying models on edge devices and optimizing for limited resources.
- Proficiency with containerization (Docker) and orchestration (Kubernetes) in production environments.
- Familiarity with model conversion tools (ONNX, TensorRT) and performance profiling.
- Solid understanding of computer vision or signal processing algorithms and a passion for cutting‑edge AI research.
Skills
pythonctensorflowdockerkubernetes