Aadvait Hirde
About
Detail
Founder & CEO
Bloomington, Indiana, United States
Résumé
Jobs
verified_user
0% verified
Founder & CEOLeverJan 2026 - Current (5 months)- National Director of CorrespondenceKappa Theta Pi NationalDec 2025 - Current (6 months)
- Founder & CEOAntrybMay 2025 - Dec 2025 (8 months)
- Project Manager: Solutions Engineering TeamLuddy Consulting AssociationFeb 2025 - Sep 2025 (8 months)・Managed a 10-member technical team through the planning and development of a custom, local LLaMA chatbot and client-facing support platform. ・Designed and prototyped the frontend experience using Framer, focusing on clean UI and intuitive interaction flows. ・Collaborated with developers to integrate the platform with Zoho CRM via API, enabling lead tracking and user data management. ・Coordinated task delegation, timelines, and weekly standups using agile workflows to ensure consistent progress across frontend, backend, and automation subteams. ・Worked closely with the client to align on feature requirements and deliver iterative updates throughout the development cycle.
- PresidentKappa Theta Pi Indiana UniversityJan 2025 - Current (1 year 5 months)・Founded the Indiana University chapter of Kappa Theta Pi, the nation’s premier professional tech fraternity, leading 15 executive board members and setting strategic direction. ・Managed internal operations—budgeting, marketing, company sponsonship, pledge curriculum, university recognition, and national communication, securing affiliation with the PFC and Kelley Student Government. ・Built an integrated application and CRM pipeline using Airtable, Google Forms, and Zapier automations to streamline applicant tracking, evaluation, and decision-making across multiple recruitment stages.
- Founding PresidentKappa Theta Pi Indiana UniversityJan 2025 - Dec 2025 (1 year)・Founded the Indiana University chapter of Kappa Theta Pi, the nation’s premier professional tech fraternity, leading 15 executive board members and setting strategic direction. ・Managed internal operations—budgeting, marketing, company sponsonship, pledge curriculum, university recognition, and national communication, securing affiliation with the PFC and Kelley Student Government. ・Built an integrated application and CRM pipeline using Airtable, Google Forms, and Zapier automations to streamline applicant tracking, evaluation, and decision-making across multiple recruitment stages.
- Machine Learning InternCognizantMay 2024 - Aug 2024 (4 months)・Developed a scalable recommendation system using Python, TensorFlow, and PyTorch, improving personalized recommendations for over 100,000 users. ・Designed and implemented feature engineering pipelines to process large-scale datasets (5TB+) using Apache Spark and Pandas, reducing preprocessing time by 30%. ・Conducted model performance analysis using precision, recall, F1 score, and ROC-AUC metrics, achieving a ~12% improvement over baseline models. ・Fine-tuned state-of-the-art transformer models (BERT, GPT) for text classification tasks, achieving a 95% accuracy rate in sentiment analysis for user reviews. ・Collaborated with a cross-functional team to deploy machine learning models in production via Flask and FastAPI, utilizing AWS SageMake
- Software Development Intern - OCI TeamOracleMay 2024 - Aug 2024 (4 months)
- Data & AI Intern - Watson & Cloud Pak TeamIBMMay 2023 - Aug 2023 (4 months)
- Software Development InternMyCaptainMay 2023 - Aug 2023 (4 months)・Architected and developed a full-stack application using Next.js 13 with Server Actions, shadcn/ui, Prisma ORM, and TypeScript, implementing server-side streaming for real-time data updates across 50,000+ daily active users. ・Built a high-performance microservices architecture using NestJS and RabbitMQ for message queuing, achieving 99.99% uptime and processing 100+ requests/second. ・Implemented an authentication system using NextAuth.js v4.22 with RBAC, integrating OAuth2.0 providers and implementing JWE encryption for sensitive data. ・Engineered a scalable payment infrastructure using Stripe API, implementing webhooks for real-time payment event handling and ensuring PCI-DSS compliance; optimized checkout flows with Stripe Elements, redu
- Machine Learning ResearcherBLAST AIJun 2022 - Aug 2022 (3 months)・Developed a stance detection model using the RoBERTa transformer, achieving 80% accuracy in predicting tweet sentiment towards Bitcoin. ・Implemented a Recurrent Neural Network (RNN) with LSTM for Bitcoin price forecasting, reaching a mean absolute error of just $1144.85 over a 5-day span. ・Utilized Twitter API for retrieving Bitcoin-related tweets and yfinance library for historical price data. ・Applied logistic regression for sentiment analysis, achieving 78% accuracy in predicting tweet sentiment. ・Integrated sklearn for data preprocessing and model evaluation, and Huggingface library for accessing pre-trained transformer models. ・Employed Adam optimizer for RNN training and used GridSearchCV and Bayesian optimization for future hyperpar
- Chief Technology OfficerThe Spectrum MillNov 2021 - Jul 2022 (9 months)• Helped develop a cover website and a Learning Management System. • Partnered with three pharmaceutical companies and raised $5,000 in grants to help train neurodivergent individuals.
- Marketing OfficerThe Spectrum MillJan 2021 - Nov 2021 (11 months)• Marketed to companies in the healthcare industry at various seminars. • Designed flyers, brochures, online advertisements, and social media content.
Education
verified_user
0% verified
- B.Sc, Computer Science and BusinessIndiana University BloomingtonJan 2023 - May 2026 (3 years 5 months)
- DComputer ScienceDelhi Private school DubaiJan 2019 - Dec 2023 (5 years)Subjects taken as part of CBSE Course: • Computer Science • Financial Markets Management • Physics • Chemistry • Mathematics • English
Projects (professional or personal)
verified_user
0% verified
Awards
verified_user
0% verified
- Curtin DEWA BCCCurtin UniversityOct 2021• Represented the school in a national business competition.
- IIgnited Mind LabIgnited Mind LabApr 2018• Won a gold medal for ranking top 20 in the Asian sub-continent.
- AASSET Talent SearchAssetApr 2018• 99th percentile in Mathematics and Science. • Qualified for ASSET Mentorship Program.
- SSIF Sastra PratibhaScience India ForumFeb 2018• International finalist, in the top 10 qualifiers nationally. • Invited to and recognized by the Indian Embassy for a stellar performance in General Science.
Publications
verified_user
0% verified
- MMNIST Digit Recognition: Real-time Handwritten Digit Classification using Convolutional Neural NetworksDec 2024This machine learning project is a real-time handwritten digit recognition system that uses TensorFlow, OpenCV, and the MNIST dataset. The main goal is to classify digits from the MNIST dataset and make predictions on live video frames from a webcam. The MNIST dataset, consisting of grayscale images of handwritten digits (0-9), is loaded and preprocessed for training. The dataset is normalized, and a simple neural network model is trained with an early stopping callback to prevent overfitting. The model consists of a flattened input layer, a hidden dense layer, and an output layer with softmax activation for multi-class classification. The model is optimized using the Adam optimizer and trained for up to 10 epochs. Once trained, the model i
- CCIFAR-10 Image Recognition: Real-time Webcam Image Classification using Convolutional Neural NetworksDec 2024This Python project is a real-time image classification system built for the CIFAR-10 dataset using TensorFlow and OpenCV. It focuses on training a Convolutional Neural Network (CNN) to classify images into ten categories such as airplanes, cars, and animals. The CIFAR-10 dataset is loaded, preprocessed, and split into training and testing datasets. Images are normalized to enhance the model’s performance during training and evaluation. The CNN model is designed with a series of convolutional layers for feature extraction, followed by batch normalization and dropout layers to improve stability and prevent overfitting. Dense layers with softmax activation handle the final classification task. The model is optimized using the Adam optimizer a
- Using Transformers and Deep Learning with Stance Detection to Forecast Cryptocurrency Price MovementIEEENov 2022The volatility of cryptocurrencies and the exclusivity of crypto communities has made cryptocurrency investment inaccessible for common people. With machine learning, harnessing social media trends that affect price in a random field like cryptocurrency will provide everybody the ability to earn money. Although existing research utilizes sentiment analysis to label posts based solely on English, this project will use NLP to perform stance detection with respect to a certain entity to make predictions. The second part of this project will apply this stance detection to real-world prices, using an RNN to turn stance data into price data. The stance detection model, RoBERTa, reached an accuracy of 80%. An independent price prediction model usi