Data Scientist with PyTorch

The team works on understanding technical and business needs and translating them into deep learning solutions for seismic data. It improves existing seismic machine learning solutions and identifies new business use cases.

• Apply and develop deep learning models, including U-Nets, CNNs, and related architectures, for denoising and structural interpretation of 2D and 3D seismic data
• Improve the accuracy, robustness, and performance of existing seismic machine learning solutions through model retraining, architecture refinement, and hyperparameter tuning
• Develop models for fault detection, horizon tracking, and seismic facies classification
• Work with Geoscientists and Geophysicists to validate model outputs against expert interpretation and well data, and incorporate their feedback
• Identify, evaluate, and propose business use cases for computer vision and deep learning across exploration and production workflows
• Follow computer vision and seismic machine learning research and assess new methods for practical application
• Apply engineering practices for reproducible experiments, model versioning, and deployment into production workflows

• Preferably 2–4 years of experience in similar roles, including hands-on deep learning experience with real-world image or volumetric data
• Understand computer vision, including image segmentation, denoising, feature extraction, and convolutional architectures
• Be proficient in PyTorch for building, training, and evaluating deep learning models
• Have expertise in U-Net, CNN, and related architectures for 2D and 3D seismic data
• Have a background in Upstream Oil & Gas, working with Geoscience and Seismic data and teams
• Understand seismic data concepts, including acquisition and processing basics, seismic attributes, noise types, and structural features such as faults and horizons
• Have strong Python skills
• English proficiency at B2 level or higher
• Будет плюсом: experience with transformer-based or self-supervised models for vision or seismic data, familiarity with MLOps tools such as MLflow, Docker, and cloud AI services (Azure, AWS, or GCP)

• Условий в вакансии нет