AI/ML Engineer and Software Engineer

I designed and developed end-to-end AI and software solutions, including data preprocessing pipelines, model-training workflows, deployment APIs, and production monitoring systems. I built machine learning models for classification, prediction, recommendation, and automation using Python, TensorFlow, PyTorch, and Scikit-learn.

I developed and deployed AI-powered chatbots using Google Gemini for natural-language interaction, customer-support automation, and information retrieval. I also implemented AI-driven identity-verification functionality using selfie-to-profile image matching to improve user authenticity and trust.

I maintained scalable RESTful AI inference services with FastAPI and Flask, integrated LLM capabilities through API-driven architectures and prompt engineering, and managed application persistence with PostgreSQL, Redis, and cloud services. I collaborated with cross-functional teams on AI product features, model evaluation, performance tracking, and production-drift monitoring.

I built an end-to-end content-refresh prioritization system using production-scale search data and a Random Forest model to identify content that could require refreshing. I developed a human-reviewed action playbook using reason codes such as STALE_CONTENT, STRIKING_DISTANCE, and LOW_CTR_HIGH_VIS.

I designed and evaluated a grouped-client validation strategy that exposed a generalization gap between random and client-grouped evaluation. I conducted feature-leakage and validation audits to separate genuine model performance from client-specific memorization.

I documented human-review rules, no-go cases, monitoring triggers, retraining criteria, limitations, and reproducibility artifacts in an academic-style ML research paper. The project positioned the model as decision support rather than an autonomous content scheduler.

I developed machine learning solutions as part of an industry-focused internship. I applied data preprocessing, exploratory data analysis, feature engineering, model development, and model evaluation practices.

I built and evaluated practical ML models with Python, Pandas, NumPy, and Scikit-learn. I worked across the machine learning lifecycle, from dataset preparation through training, optimization, and evaluation.

I developed AI and machine learning solutions during an industry-focused Artificial Intelligence Engineering internship. I built a rule-based conversational AI chatbot in Python with intent recognition, decision logic, date and time processing, conversational handling, and chat-history persistence.

I developed an end-to-end supervised classification pipeline for e-commerce order-status prediction. The workflow covered preprocessing, missing-value handling, categorical encoding, feature preparation, train/test splitting, and model serialization.

I trained and compared Logistic Regression and Random Forest models using Scikit-learn, evaluating them through accuracy measures, classification reports, and confusion matrices. I used Pandas, NumPy, Joblib, Matplotlib, and Seaborn for analysis, development, evaluation, and visualization.

I completed a Generative AI consulting job simulation focused on developing an AI-powered financial assistant for a global consulting use case. I built a financial chatbot capable of interpreting company financial reports, including 10-K and 10-Q filings, and generating user-friendly insights.

I used Python and Pandas for financial-data processing, transformation, and analysis. I also developed Django backend components to provide personalized financial insights and user-specific data views.

Completed an NCV qualification in Engineering and Related Design.

Completed studies in introductory video game creation.