Machine Learning Engineer | Data-Driven Problem Solver | AI for Business Impact

I am currently pursuing my B.Tech in Computer Science Engineering (2022–26), with a strong focus on Machine Learning, Artificial Intelligence, and Data-Driven Decision-Making.

My passion lies in developing intelligent systems that solve real-world problems and creating measurable business outcomes. With experience in Computer Vision, NLP, and Explainable AI, I aim to build solutions that are technically robust and strategically relevant.

• Machine Learning Enthusiast: Skilled in building, training, and deploying models using CNNs, YOLO, NLP techniques, and U-Net architectures.
• Data Strategy Mindset: I believe in aligning AI solutions with key business metrics to ensure impact beyond accuracy scores.
• Industry Exposure: Currently interning at RMSI Pvt. Ltd., working on ML applications using OpenCV, CNN, YOLO, and NLP.
• Certified Expertise: Advanced coursework in Machine Learning, Deep Learning, and GenAI from Stanford University and industry job simulations from leading global organizations.

• Programming & ML: Python, C++, TensorFlow, PyTorch, Keras, OpenCV, Scikit-learn
• Data Handling & Visualization: Pandas, NumPy, Matplotlib, Seaborn
• AI Specialties: Computer Vision, NLP, Model Explainability, Adversarial Robustness
• Tools: Git, Jupyter, Google Colab, Visual Studio Code

• Problem: How can we ensure that explainability methods remain reliable under adversarial attacks?
• Solution: Designed a framework that identifies vulnerabilities in popular explainability methods and implemented techniques to improve robustness.
• Impact: Strengthened trust in AI models for critical decision-making environments; reduced misleading explanations by >30% compared to baseline.
• Tech: Python, CNN, Adversarial ML, Explainable AI

• Problem: Autonomous vehicles require accurate lane detection for navigation in diverse real-world conditions.
• Solution: Developed a deep learning-based lane detection model using U-Net and OpenCV preprocessing, trained on thousands of annotated road images.
• Impact: Achieved ~90% IoU in real-time lane detection, reducing detection errors significantly, enabling safer and more reliable autonomous navigation.
• Tech: Python, Keras, OpenCV, CNN

• Problem: Manual resume screening is time-intensive and prone to human error in recruitment processes.
• Solution: Built a resume parser leveraging NLP for automatic information extraction (skills, experience, contact details).
• Impact: Reduced screening time by 80%, enabling HR teams to focus on strategic decision-making.
• Tech: Python, NLP, Regex, Tkinter

• Problem: Understanding climate patterns is crucial for long-term planning in multiple sectors.
• Solution: Implemented a time-series forecasting model to predict weather patterns using historical data.
• Impact: Provided actionable insights for agricultural planning, disaster management, and resource allocation.
• Tech: Python, Scikit-learn, Pandas, Matplotlib

• Advanced Learning Algorithms – Stanford University (2025)
• Machine Learning Specialization – Stanford University (2024)
• Data Science Job Simulation – Commonwealth Bank (2024)
• GenAI Job Simulation – BCG X (2024)

1. Define the Right Problem: Understanding the business/operational need before jumping into data.
2. Design Data-Driven Solutions: Building ML models tailored to deliver measurable outcomes.
3. Ensure Robustness: Focusing on reliability, interpretability, and scalability.
4. Deliver Value: Aligning results with KPIs to ensure real-world relevance.

"Creating AI solutions that are as valuable to businesses as they are innovative in technology."