A data-driven engineer focused on building robust machine learning pipelines, optimizing complex algorithms, and translating complex data architectures into scalable, real-world solutions.

An end-to-end Machine Learning pipeline optimized for predicting and mitigating supply chain logistics carbon footprints.

• The Challenge: Handling multi-dimensional, noisy logistical datasets to accurately forecast environmental impacts.
• The Solution: Engineered robust data processing and transformation pipelines utilizing Pandas and NumPy to feed structured feature sets into optimized regression models.
• Tech Stack: Python, Jupyter Notebook, Scikit-Learn, Predictive Modeling.
• Key Outcome: Created a scalable framework that demonstrates an ability to translate sustainability goals into quantitative algorithmic solutions.

A structured, data-managed tracking repository engineered to solve premium company-wise Data Structures and Algorithms patterns.

• The Focus: Systematizing core algorithmic problem-solving (Graphs, Trees, Dynamic Programming, System Design).
• Why it matters: Proves enterprise-level preparation and a deep mathematical understanding of computational complexity ($O(N)$ optimization).
• Tech Stack: C++, Python, Markdown Data Analytics, CSV Matrix.

• Production-Grade Pipeline Design: Moving beyond static Jupyter notebooks. Focusing on modular, repeatable ETL and ML training loops that handle data drift and messy real-world logistics datasets.
• Algorithmic Rigor: Deep structural understanding of execution time and memory footprints. Applying optimized Data Structures and Algorithms ($O(1)$ and $O(\log N)$ targets) directly to heavy data processing layers.
• Mathematical & Statistical Precision: Rigorous approach to loss functions, performance validation metrics (RMSE, MAE, F1-Score), and mathematical data transformations to ensure predictive models are mathematically sound, not just lucky.