- Technical driven environment
- International and flexible team
- Competitive salary
About The Opportunity
Our client is seeking a skilled Computer Vision / Machine Learning Engineer to join a team building next-generation Digital Twin solutions for real-world operational environments.
This role focuses on applying advanced computer vision and deep learning techniques to detect, track, and analyze assets, people, and equipment in large-scale logistics and industrial settings. The successful candidate will help develop production-grade AI solutions that bridge the physical and digital worlds, enabling real-time operational insights and automation.
This is an excellent opportunity for engineers who are passionate about computer vision, deep learning, and deploying AI systems at scale.
Key Responsibilities
- Design, develop, train, and optimize deep learning models for computer vision applications.
- Build solutions for object detection, multi-object tracking, classification, and segmentation.
- Develop systems capable of detecting and tracking workers, vehicles, packages, and other operational assets in real-world environments.
- Build and maintain data pipelines for collection, preprocessing, annotation, and augmentation of training datasets.
- Evaluate model performance using metrics such as mAP, precision, recall, and inference latency.
- Integrate trained models into Digital Twin and operational monitoring platforms.
- Optimize models for production deployment, focusing on scalability, performance, and reliability.
- Research and prototype emerging AI/ML technologies to enhance existing solutions.
- Collaborate with software engineers and data engineers to improve ML infrastructure and deployment workflows.
- Partner with stakeholders to translate business requirements into effective AI solutions.
- Monitor production models and proactively address performance degradation and operational issues.
- Maintain high standards for code quality, documentation, reproducibility, and maintainability.
Required Qualifications
- 5+ years of hands-on Machine Learning or Computer Vision engineering experience, or a PhD in Computer Science, Electrical Engineering, or a related field with 2+ years of industry experience.
- Strong expertise in computer vision, including:
- Object Detection
- Multi-Object Tracking
- Instance Segmentation
- Advanced Python programming skills.
- Hands-on experience with PyTorch and/or TensorFlow.
- Experience across the full machine learning lifecycle, including:
- Data collection and annotation
- Model training and optimization
- Hyperparameter tuning
- Evaluation and validation
- Production deployment
- Strong understanding of machine learning fundamentals, optimization techniques, loss functions, regularization, and evaluation methodologies.
- Experience deploying and operating ML models in production environments.
- Experience with model benchmarking, validation, and dataset quality management.
Preferred Qualifications
- Experience beyond computer vision in areas such as:
- Generative AI
- Large Language Models (LLMs)
- NLP
- Reinforcement Learning
- Anomaly Detection
- Experience with MLOps platforms and tools such as:
- MLflow
- Weights & Biases
- DVC
- Kubeflow
- Experience training and deploying models on AWS, GCP, or Azure.
- Familiarity with 3D Computer Vision, LiDAR, point cloud processing, or sensor fusion technologies.
- Experience building scalable AI systems in production environments.
Language Requirements
- Business-level English
- Japanese language skills are a plus
Why Consider This Opportunity?
- Work on cutting-edge Computer Vision and Digital Twin technologies.
- Contribute to real-world AI applications with measurable operational impact.
- Exposure to large-scale ML systems and production deployment challenges.
- Opportunity to influence the evolution of AI initiatives beyond Computer Vision.
- Collaborate with highly skilled engineers in Machine Learning, Data Engineering, and Software Development.
To apply or learn more, please contact Anqi Chen and send your resume to [email protected].