
Senior Data Scientist
- New Castle, DE
- Permanent
- Full-time
- Develop machine learning and statistical models for interpreting complex rheology and thermal analysis data (e.g., DSC, TGA, DMA).
- Implement advanced signal processing, noise reduction, and feature extraction methods for time-series and spectral data.
- Collaborate with R&D to integrate data-driven features into instrument software.
- Prototype AI-assisted methods for experiment optimization and anomaly detection.
- Build and maintain reproducible, scalable data pipelines for experimental datasets.
- Ensure compliance with data quality, storage, and metadata standards.
- Partner with scientists to define analytical needs and translate them into technical requirements.
- Present findings to both technical and non-technical audiences
- Participate in all team meetings and ceremonies in direct collaboration with other sites, provide input and feedback, take ownership on identified improvements.
- Actively participate in learning and sharing activities either during informal or formal training and demos.
- Demonstrate continuous technical improvement.
- M.S. or Ph.D. in Data Science, Materials Science, Applied Physics, Chemical Engineering, or related field.
- 5+ years of experience in data science, with significant exposure to thermal analytics and/or rheology.
- Strong programming skills in Python (NumPy, Pandas, scikit-learn, PyTorch/TensorFlow) and data visualization tools (Matplotlib, Plotly).
- Expertise in time-series analysis, multivariate statistics, and machine learning.
- Proven track record of translating domain-specific problems into robust analytical solutions.
- Experience integrating ML algorithms into scientific instruments or laboratory software.
- Familiarity with rheological models, viscoelastic properties, and thermomechanical analysis techniques.
- Knowledge of cloud-based data storage and computation frameworks.
- Strong publication or patent record in relevant fields.
- Mentor junior team members and interns in best practices for coding, analysis, and domain-specific modeling.
- Foster cross-functional knowledge sharing between data science and materials science teams.