AI Engineer - Model Optimization & Edge AI
ClosedDeep Learning Collaborating Pytorch
Location
Job Overview And Responsibility
• Fine-tune pretrained deep learning models (CNN/Transformer) on task-specific datasets (e.g., classification, detection, segmentation). • Apply model compression techniques: quantization (PTQ/QAT), pruning, knowledge distillation, etc. • Convert models to deployment-ready formats (ONNX, TensorRT, OpenVINO...). • Optimize model inference for edge deployment: latency, FPS, throughput, memory footprint. • Benchmark performance on different platforms: Jetson, ARM, Qualcomm SNPE, OpenVINO, or AI SDKs. • Collaborate with the software and hardware teams to validate models in production environments. • Maintain and improve MLOps pipeline: training logs, version control, artifact tracking.
Required Skills and Experience
• Bachelor's degree or higher in Computer Science, Data Science, EE, or related fields. • 2+ years of experience in deep learning (PyTorch or TensorFlow). • Hands-on experience with model optimization techniques and deployment. • Familiar with ONNX, TFLite, TensorRT, or similar deployment frameworks. • Understanding of inference performance metrics (latency, FLOPs, memory usage).
Why Candidate should apply this position
• Benefits will be shared in detail with successful candidates.
Preferred skills and experiences
• [Nice to have] Experience deploying models on edge devices: Jetson Nano/Xavier, Qualcomm QCS, Intel Movidius, Raspberry Pi + NPU... • [Nice to have] Familiarity with video analytics or embedded vision (e.g., YOLO, MobileNet, EfficientNet). • [Nice to have] Exposure to MLOps tools: MLflow, Weights & Biases, TensorBoard, Docker. • [Nice to have] Prior work in AI applications such as smart cameras, smart cities, industrial AI, etc.
Completed jobs (27)
