Job
- Level
- Senior
- Job Feld
- Data, Back End
- Anstellung
- Vollzeit
- Vertragsart
- Unbefristetes Dienstverhältnis
- Gehalt
- ab 53.802 € Brutto/Jahr
- Ort
- Wien
- Arbeitsmodell
- Onsite
Job Zusammenfassung
In dieser Position entwickelst du fortgeschrittene Machine Learning Modelle mit PyTorch v2, implementierst Zeitreihenanalysen und gestaltest skalierbare Datenpipelines, wobei du eng mit Fachleuten zusammenarbeitest.
Job Technologien
Deine Rolle im Team
- Design, develop, and deploy advanced machine learning models for process modeling and optimization, with a focus on PyTorch v2 and PyTorch Lightning.
- Implement and benchmark diverse modeling approaches: physics-informed neural networks (PINNs), hybrid mechanistic-ML models, and complementary frameworks.
- Research, evaluate, and integrate open-source alternatives to ensure the platform uses the latest best practices in scientific modeling.
- Build and optimize time-series analysis systems for process monitoring and predictive control.
- Architect and implement distributed training and inference using Ray (primary) and other distributed computing frameworks.
- Develop scalable data pipelines and ETL processes for process data integration and analysis.
- Collaborate closely with modeling engineers and domain experts to translate scientific requirements into ML solutions.
- Implement MLOps practices using MLflow (primary) and alternative experiment tracking and model versioning tools.
- Build comprehensive data validation, profiling, and monitoring systems to ensure data quality and model reliability.
- Design and maintain RESTful and gRPC APIs for ML model serving and real-time inference.
- Implement hyperparameter tuning using Ray Tune and other optimization frameworks.
- Optimize models for GPU utilization and distributed computing performance.
- Contribute to statistical analysis, experimental design, and scientific method validation for process models.
- Write maintainable, well-tested code following team quality standards and participate in code reviews.
Unsere Erwartungen an dich
Ausbildung
- Master's degree or higher in Computer Science, Data Science, Machine Learning, Mathematics, Physics, Chemical Engineering, or a closely related technical field.
Qualifikationen
- Expert-level Python programming skills (core constructs, modules, packaging: UV, Poetry, pip).
- Deep expertise in PyTorch v2 and PyTorch Lightning for building, training, and deploying ML models in production.
- Strong mathematical and statistical background including optimization algorithms, numerical methods, and statistical modeling.
- Knowledge of GPU optimization and distributed computing for efficient model training and inference.
- Proficiency with data validation, profiling, and analysis tools and methodologies.
- Knowledge of RESTful and gRPC APIs for ML model serving and microservices integration.
- Strong grasp of key design patterns and practices (e.g., DDD, SOLID, DRY, KISS, Composition, Inheritance).
- Knowledge of cloud platforms (AWS, GCP, or Azure) and containerization with Kubernetes.
- Excellent written and verbal communication skills in English.
Erfahrung
- 5+ years' professional experience in machine learning, data science, or scientific computing with production ML systems.
- Strong experience with the Python data science stack: Pandas, NumPy, Scikit-learn, and Jupyter ecosystems.
- Experience with distributed computing and scaling ML workloads using Ray (preferred), Spark, or Dask.
- Hands-on experience with time-series analysis, regression modeling, and statistical methods for scientific data.
- Experience with MLOps tools and practices: MLflow (preferred) for experiment tracking, model versioning, and lifecycle management.
- Experience with hyperparameter tuning and optimization frameworks (Ray Tune preferred, Optuna, or similar).
- Experience with specialized ML libraries for time-series, regression, and differential equations.
- Experience designing and operating data pipelines, ETL workflows, and data warehouse solutions.
- Experience with Docker & Docker Compose, and comfortable developing on Ubuntu (WSL2) environments.
- Strong Git workflows, CI/CD fundamentals, and Agile/Scrum collaboration experience.
Job Standorte
Themen mit denen du dich im Job beschäftigst
Das ist dein Arbeitgeber
Novasign
Als Spin-off der Universität für Bodenkultur Wien (BOKU) bietet Novasign innovative Softwarelösungen zur Optimierung von Bioprozessen an. Das 2019 gegründete Unternehmen hat seinen Sitz in Wien und unterstützt Kunden in der Biopharmazeutik mit fortschrittlichen Technologien.
Description
- Unternehmenstyp
- Startup
- Arbeitsmodell
- Onsite
- Branche
- Pharma, Chemie, Biotech