Motorola Solutions

Tóm tắt công việc

• Support the team in data collection, curation, annotation quality control, and edge case analysis to improve model robustness for Video Analytics problems.
• Research and train lightweight/experimental AI models (CNNs, Object Detection/Tracking, Vision Transformers, VLMs) to build PoCs (Proof of Concepts) for new ideas.
• Assist in optimizing and converting AI models using frameworks like PyTorch, TensorFlow/TensorFlow Lite, ONNX, or TensorRT for deployment.
• Conduct initial benchmarking and performance analysis of Computer Vision models on target device platforms (e.g., NVIDIA, Intel, edge hardware).
• Work closely with senior engineers to debug data/model issues, implement fixes, and optimize inference pipelines.
• Document experiment workflows, data findings, edge case insights, and PoC results to contribute to team knowledge sharing.

• Compensation & bonus: 13th & 14th salary, AIP bonus, Holidays, Tet, and Long year service …
• Social insurance, Health insurance, Unemployment insurance: by Social Insurance and Labor Law
• The regime of annual leave, company trip, and checkup examination
• Award for marriage, newborn
• We have AON insurance package for employee, spouse, and children every year
• You will be trained, learned & work with the best technical managers who help you improve various dev skills & career path
• You’ll love working in our dynamic environment employees, young & active
• We love sport activities, as marathon, football, swimming,...
• Working time: From Monday to Friday | 08:30-12:00 & 13:00-17.30

• Final-year student (Bachelor's degree) in Computer Science, Machine Learning, Data Science, or a related technical field.
• Basic understanding of Machine Learning and Computer Vision concepts & architectures (e.g., CNNs, YOLO, Vision Transformers/VLMs), including training and evaluation metrics.
• Proficiency in Python and familiarity with Deep Learning frameworks (PyTorch or TensorFlow) and Image Processing libraries (OpenCV).
• Strong analytical mindset, detail-oriented, and effective at identifying data anomalies or edge cases.
• High creativity, eager to learn, proactive attitude, and capable of solving problems both independently and within a team.
• Good reading and writing skills in English (capable of reading technical papers, documentation, and writing reports).

Preferred Qualifications

• Relevant coursework, personal projects, or prior internships in Computer Vision, Image Processing, or Video Analytics (e.g., Object Detection, Tracking, Action Recognition, Re-ID).
• Experience with model conversion/quantization tools (ONNX, TensorRT, OpenVINO, TFLite) or basic C/C++/CUDA programming is a plus.
• Active participation in tech communities, AI/ML hackathons, or Kaggle competitions.