Company Background
The company is a leading German technology company specializing in digital dentistry and healthcare solutions, with over 80 years of innovation and a global presence across 174 countries. Employing more than 1,350 professionals worldwide and generating over €374 million in annual revenue in 2024, the company is recognized for its advanced dental imaging systems, diagnostic software, infection prevention technologies, and AI-powered solutions. As part of its global digital transformation strategy, the company is expanding its software development and AI R&D hub in Malaysia to develop next-generation cloud-based platforms and computer vision solutions that support dentists in delivering more accurate and efficient patient care.
Office Location
Menara Sunway, Selangor
Working Mode
Hybrid (3 days office; 2 days home)
Job Responsibilities
- Deliver complex machine learning pipelines across data preparation, model development, evaluation, deployment, and monitoring.
- Perform applied research on deep learning models for medical image segmentation, detection, and classification across imaging modalities (e.g. radiographs, CBCT, volumetric data).
- Design rigorous evaluation frameworks by preparing clinically meaningful metrics and test sets.
- Collaborate with clinical and annotation teams on labeling strategy, inter-rater agreement, and active-learning rounds to improve dataset quality.
- Build and maintain model pipelines to ensure efficient data loading, reproducible training/evaluation, and versioned artifacts.
- Design and own the model serving layer that includes pre-processing, inference, post-processing, and composition.
- Instrument production models with monitoring for prediction quality, input drift, and data integrity to feed real-world failure cases back into the data and retraining pipeline.
- Uphold standards for experimentation and engineering best practices by conducting code, design, and experiment reviews and mentoring less-experienced engineers.
Job Requirements
- Proven experience in machine learning, computer vision, or a related engineering field.
- Strong proficiency in Python across the scientific and ML stack with the ability to write maintainable, production-grade code.
- Experience preparing imaging datasets for deep learning and curating well-defined train/test splits that prevent leakage.
- Ability to design and run deep learning experiments — appropriate architectures and loss functions, controlled ablations, and sensible baselines — with sound interpretation of results.
- Strong understanding of evaluation methodology and applied statistics for model validation.
- Hands-on experience with CV libraries (e.g. OpenCV, albumentations) and modern ML frameworks (e.g. PyTorch, JAX, Tensorflow).
- Familiarity with experiment tracking and reproducibility tooling (e.g. MLflow, Weights & Biases).
- Excellent communication skills and cross-functional collaboration.
- Bachelor's or Master's degree in a STEM field, or equivalent practical experience.
- Nice to have: medical imaging, active learning, MLOps practices, or model serving frameworks.