Machine Learning - Internship

Selected intern's day-to-day responsibilities include:

1. Analyze and preprocess noisy, real-world health and sensor data using
statistical and signal processing techniques
2. Design and implement signal cleaning, filtering, denoising, and feature
extraction pipelines
3. Apply time-series analysis, spectral analysis, and statistical modeling to
interpret complex data patterns
4. Develop and train machine learning models on preprocessed signals for
prediction, classification, or anomaly detection
5. Evaluate data quality and identify artifacts, outliers, and
inconsistencies in raw datasets
6. Collaborate with cross-functional teams to understand data sources, sensor
behavior, and real-world constraints
7. Validate models using appropriate statistical metrics and experimental
design principles
8. Optimize algorithms for performance, robustness, and scalability
9. Document assumptions, methodologies, and findings clearly for technical
and non-technical stakeholders
10. Iterate rapidly on experiments, incorporating feedback from real-world
data observations
11. Stay updated with advances in signal processing, applied statistics, and
ML techniques relevant to healthcare data