Machine Learning Engineer with Mathematical Foundations
I design machine learning systems grounded in mathematical principles such as optimization, probability, and dynamical systems.
PhD in Mathematics (Topological Dynamics & Ergodic Theory) from BITS Pilani.
Core Tech Stack
Python
PyTorch
TensorFlow
Scikit-learn
SQL
Generative AI
Key Projects
Placement Predictor ML System
- Problem statement: Predict student placement outcomes based on academic profiling metrics.
- Dataset size: ~10,000 records
- Models tested: Logistic Regression, Random Forest, XGBoost
- Evaluation metrics: F1-Score, ROC-AUC
- Final model performance: 94% accuracy with optimized Random Forest
Predictive Modeling for Agriculture
- Problem statement: Identify the single soil feature that best predicts crop type due to testing cost constraints.
- Dataset size: 2,200 soil samples across 22 crops
- Models tested: Decision Trees, Gradient Boosting
- Evaluation metrics: Precision, Recall
- Final model performance: Maintained 85% accuracy using only 1 distinct feature
OpenAI API Travel Assistant
- Problem statement: Design deterministic structured responses for localized Parisian tourist queries.
- Dataset size: Dynamic API-fed conversational queries
- Models tested: GPT-3.5-Turbo, GPT-4
- Evaluation metrics: Response latency, JSON Schema adherence
- Final model performance: 100% successful schema adherence
GitHub Activity
Teaching & Mathematical Foundations
Academic Rigor & Mentorship
With a solid academic foundation in advanced mathematics and teaching experience across diverse university courses, I specialize in translating complex theoretical concepts into practical intuition. My background ensures my machine learning systems are mathematically robust, optimizable, and carefully evaluated.
View Teaching PortfolioLet's Connect
Interested in building ML systems with mathematical rigor?
Let's collaborate.
Start a Conversation