@ · /github (opens in a new tab) · /linkedin (opens in a new tab) · /leetcode (opens in a new tab)

👋 Hi, I'm Aditya! I'm an AI/ML Engineer based in New York, NY. I build production machine learning systems using XGBoost, PyTorch, and TensorFlow, and deploy scalable ML pipelines on AWS SageMaker and Lambda with real-time inference via FastAPI. Currently pursuing my MS in Computer Science at Pace University, expected May 2026.

Skills

ML & AI: TensorFlow, PyTorch, Scikit-learn, XGBoost, SHAP, SVD, Feature Engineering, Recursive Feature Elimination (RFE), MLOps, Collaborative Filtering, Survival Analysis Languages: Python, JavaScript (ES6+), TypeScript Cloud & DevOps: AWS (SageMaker, Lambda, EC2), Docker, FastAPI, Google Cloud Platform Frameworks & Libraries: React, Node.js, Express.js, Flutter, SwiftUI Databases & APIs: PostgreSQL, MySQL, MongoDB, Firebase, REST APIs Tools: Git, GitHub Actions, Postman

Work

PNC : AI/ML Engineer

Duration: Dec 2025 – Current | New York, NY

• Performed feature engineering and data preprocessing on trading transaction data using Python and Pandas, applying recursive feature elimination (RFE) to improve model accuracy by 15% and cut feature dimensionality by 30%.
• Engineered classification models with Scikit-learn and PyTorch (Random Forest, XGBoost) to predict trade settlement likelihood, hitting an 87% AUC-ROC score and streamlining compliance review for operations teams.
• Built an AI-powered client risk assessment system using Python, Pandas, and logistic regression with survival analysis, enabling risk management for 80 high-value investment banking clients.
• Developed a predictive analytics pipeline with XGBoost regression to forecast client portfolio risk exposure, improving capital allocation accuracy by 20% and reducing pricing error rate by 12%.
• Deployed inference APIs with FastAPI and Docker on AWS EC2, integrating OpenAI and Hugging Face APIs for trade document summarization at 99% uptime with low-latency inference.

Get SuperStars Inc. : Software Developer Intern

Duration: July 2025 – Sep 2025 | New York, NY

• Built and shipped core mobile features for a video-first platform enabling video resumes, pitches, and short-form content discovery, using Flutter and Dart across a distributed, production-scale app.
• Engineered a real-time Stories feed with live content updates using WebSockets and Provider for state management, improving feed load speed by 22% for 15,000+ active users.
• Developed the user profile ("Me") tab and notifications module supporting real-time alerts and interactions, using Flutter, Dart, and Provider across the app's core navigation experience.

Vivma Software Inc : AI/ML Engineer

Duration: Aug 2022 – Aug 2024 | India

• Designed a securities recommendation engine for a capital markets platform using collaborative filtering with SVD in Python and TensorFlow, achieving a 24% improvement in client conversion rates and reducing portfolio churn by 11%.
• Developed a real-time algorithmic pricing model with XGBoost and Scikit-learn for a fixed income client, processing 50K+ instruments hourly at sub-100ms inference latency and increasing annual trading revenue by 16%.
• Implemented an end-to-end MLOps pipeline using Docker and AWS SageMaker to automate model training, validation, and deployment, cutting the retraining cycle from 8 hours to 45 minutes.
• Engineered feature selection and preprocessing workflows on 2M+ client transaction records, applying SHAP-based feature importance analysis to improve credit risk model F1 score by 19% across three production models.
• Integrated XGBoost and Random Forest models into production AWS Lambda microservices via FastAPI, serving real-time market risk scoring for 200K+ daily trade requests at sub-150ms latency with zero downtime during peak hours.

Projects

Iris Scan Detection & Authentication System

React, Node.js, MediaPipe, FAISS

Built a real-time biometric authentication system that uses your iris. yes, your actual eye, to verify who you are. It pulls 128-dimensional embeddings from a live webcam stream using MediaPipe FaceMesh and matches identities via cosine similarity. Plugged in FAISS for fast vector search so the whole thing runs in under 2 seconds end-to-end with 95%+ accuracy. Full MERN stack, secure REST APIs, cloud-hosted and production-ready. 🔗 GitHub (opens in a new tab) | 🌐 Live Demo (opens in a new tab)

AI Hunger Games: Multi-Agent Evolutionary Simulation

Python, LLMs

What happens when you put a bunch of AI agents with different personalities in a room and make them compete? That's this project. Each agent generates responses, votes on others, and fights to survive across rounds. There's also a genetic evolution engine under the hood — agents inherit traits, mutate, and form alliances. All the data (survival rates, voting patterns, lineage) gets exported as JSON/CSV for analysis. 🔗 GitHub (opens in a new tab)

Open-Source Contributor Moltbot (opens in a new tab) (Core Engine of Clawbot AI (opens in a new tab))

Built a SwiftUI audio player with regex-based parsing and multi-format support (OPUS, WAV) for real-time media interactivity inside a viral agentic platform. Also refactored TypeScript metadata and frontmatter parsing for Clawbot's skill repository.

Education

Pace University MS in Computer Science, New York, NY Expected May 2026 | Pace Software Developer Club

University of Mumbai BS in Computer Science, India May 2024 | IEEE & Terna Code Camp

Publications

Credit Card Fraud Detection Using Machine Learning Designed and evaluated fraud detection models using Random Forest, Logistic Regression, and Naïve Bayes on 4,000+ financial transactions. If you're into ML research, this one's worth a read. 🔗 View Publication (opens in a new tab)

🎶💻📚

I enjoy coding side projects, exploring AI tools, listening to music, reading tech blogs, and keeping up with the latest in software engineering.