We’re seeking a Deep Learning Data Scientist to join our research-driven team developing real-time recommendation systems for industrial production environments. You'll be responsible for designing, training, and evaluating deep learning models that help optimize processes, detect anomalies, and uncover hidden patterns in sensor, control, and video data.
In addition to time-series and sensor analysis, you will develop computer vision models that process video streams for object detection, tracking, and quantitative analysis, directly impacting productivity, quality, and efficiency in our customers’ factories.
This is a hands-on role for someone passionate about solving challenging real-world problems using modern machine learning techniques. You'll collaborate closely with other researchers, data engineers, and system developers to bring your models to life.
· Design and implement deep learning models tailored to time-series sensor data, control system behavior, video streams, and anomaly detection.
· Develop custom architectures (e.g., RNNs, Transformers, Autoencoders, CNNs, object detection, segmentation, and quantitative analysis models).
· Conduct thorough experimentation and benchmarking to evaluate model performance and robustness.
· Build and maintain datasets from production environments, including annotation and preprocessing of video data.
· Optimize models for runtime performance, interpretability, and real-time video inference in critical systems.
· Collaborate with research engineers to integrate DL components into production pipelines.
· Stay current with state-of-the-art research in deep learning, computer vision, and industrial AI, and assess its applicability to our domain.
· M.Sc. or Ph.D. in Computer Science, Machine Learning, Electrical Engineering, or a related field.
· 3+ years of experience developing deep learning models, ideally for time-series or video data.
· Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.
· Strong understanding of model architectures, training dynamics, overfitting prevention, and evaluation strategies.
· Experience working with noisy or incomplete real-world data.
· Ability to independently run experiments, interpret results, and iterate quickly.
· Hands-on experience with computer vision models (e.g., CNNs, YOLO, Mask R-CNN, EfficientDet).
· Familiarity with anomaly detection, predictive maintenance, or industrial control systems.
· Experience with vision systems in production environments.
· Knowledge of signal processing, control theory, or process optimization.
· Experience with 3D reconstruction, point cloud processing, or geometry-based methods for object analysis.
· Experience with MLOps tools (e.g., MLflow, DVC, Weights & Biases).
· Exposure to hybrid model architectures (combining physics-based and data-driven approaches).
· Familiarity with computer vision libraries such as OpenCV, Detectron2, or MMDetection.
