Aryan Tiwari

Data Pipeline Engineering: Designed and optimized real-time data pipelines to process high-frequency sensor data, utilizing statistical analysis to detect system anomalies with high precision.

MLOps & Automation: Built automated verification and validation pipelines (CI/CD) to streamline model deployment, reducing manual testing overhead and ensuring data integrity.

Signal Processing: Developed high-throughput signal-processing pipelines for real-time inference, enabling predictive maintenance and fault detection before critical failure.

Embedded Machine Learning Intern at ADHVX Industries (2026-01 – Present)

• Data Pipeline Engineering: Designed and optimized real-time data pipelines to process high-frequency sensor data, utilizing statistical analysis to detect system anomalies with high precision.
• MLOps & Automation: Built automated verification and validation pipelines (CI/CD) to streamline model deployment, reducing manual testing overhead and ensuring data integrity.
• Signal Processing: Developed high-throughput signal-processing pipelines for real-time inference, enabling predictive maintenance and fault detection before critical failure.

Research Scholar at CV Raman University (2026-01 – Present)

• Data Science Pipeline: Engineered an end-to-end data science pipeline for a massive 982-hour time-series dataset, executing advanced preprocessing, artifact rejection, and sliding-window segmentation.
• Statistical Benchmarking: Conducted rigorous statistical benchmarking and ablation studies to evaluate model performance metrics, achieving a 99.99% reduction in computational complexity while maintaining 90% sensitivity.
• Research Collaboration: Collaborated on cross-functional research initiatives to translate complex model architectures into interpretable findings for external stakeholders.

Machine Learning Intern at AICTE Eduskills (2024-07 – 2024-09)

• Large-scale Data Management: Managed and preprocessed large-scale structured datasets (50,000+ data points), implementing advanced feature development and data augmentation techniques to improve model generalization by 12%.
• Hyperparameter Optimization: Utilized experimentation frameworks to optimize hyperparameters, driving a 30% reduction in training time while maintaining high precision and recall metrics.

Bachelor of Technology in Artificial Intelligence – SRM Institute of Science and Technology (2023-08)