👋 Hey there — I’m Aryan Maheshwari
AI Engineer | M.S. Applied Data Science @ USC | Building Production-Ready ML Systems & Autonomous Driving Solutions
AI Engineer | M.S. Applied Data Science @ USC | Building Production-Ready ML Systems & Autonomous Driving Solutions
I'm Aryan Maheshwari, an AI Engineer currently pursuing my M.S. in Applied Data Science at the University of Southern California, with a strong foundation from my B.Tech in Artificial Intelligence and Data Science from K.J. Somaiya Institute of Technology.
My passion lies in the intersection of machine learning, software engineering, and research. I've had the privilege of working across diverse domains: from developing ML models for autonomous vehicles at USC Autodrive Lab to building production-ready AI systems at Convexia (YC'25), and leading cross-functional teams at USC Games.
What drives me is the challenge of taking complex AI research and turning it into scalable, production-ready solutions. Whether it's engineering perception models for autonomous driving, building hybrid AI systems for sports analytics, or developing toxicity evaluation pipelines with 100% reproducibility — I thrive on the technical depth and real-world impact.
My technical expertise spans the full ML stack: from deep learning frameworks (TensorFlow, PyTorch) and MLOps (MLflow, CUDA) to cloud infrastructure (AWS, GCP, Azure) and modern AI tools (LangChain, GPT-4, RAG systems). I'm particularly drawn to reinforcement learning, computer vision, and the emerging field of AI-powered decision systems.
Beyond technical skills, I believe in the power of collaboration and knowledge sharing. I've published research papers on AI evolution and blockchain-based systems, and I'm always excited to work on projects that push the boundaries of what's possible with AI.
Let's build the future of AI together.
Master of Science in Applied Data Science
Pursuing advanced studies in data science with focus on machine learning, statistical modeling, and real-world applications. Coursework includes advanced algorithms, big data analytics, and AI systems design.
Bachelor of Technology in Artificial Intelligence and Data Science
Comprehensive undergraduate program covering AI fundamentals, machine learning algorithms, data structures, and blockchain technology. Specialized coursework in deep learning, computer vision, and natural language processing.
High School Diploma
Completed higher secondary education with focus on science and mathematics. Strong foundation in physics, chemistry, and mathematics that provided the groundwork for engineering studies.
10th Grade, ICSE Board
Completed secondary education with 92% grade. Strong foundation in English and Hindi languages, along with comprehensive curriculum covering science, mathematics, and social studies.
AI-powered educational platform with RAG-based Q&A, quiz/flashcard generation, and real-time chat. Integrates GPT-4, LangChain, Chroma, FastAPI, and Next.js, enabling 10,000+ pages of textbook ingestion with sub-2s query latency and scalable deployment on AWS Fargate.
Created end-to-end toxicity evaluation pipeline integrating 6 ML models with MLflow tracking, SHAP-based feature visualization, and confidence/disagreement detection across organ-toxicity modules, ensuring 100% reproducibility.
Scalable multi-level text retrieval framework integrating Gaussian Mixture Models, GPT-4-turbo, BM25, and semantic search (SPIDER). Enables granular content extraction from 300+ page academic textbooks while improving re-ranking precision by 30% and ensuring low-latency query execution.
Built fault-tolerant distributed job scheduler with REST/gRPC APIs, Redis-backed queues, and worker pools, achieving 100k+ daily task executions with < 100ms scheduling latency under high concurrency.
End-to-end histopathology image classification pipeline using MobileNetV2, achieving 92% accuracy on IDC detection. Integrated Grad-CAM for interpretability, deployed DCGAN for synthetic data augmentation, and built interactive Streamlit app for real-time predictions with modular, production-ready architecture.
Gymnasium + PPO + Apple MPS with training logs and policy video
Custom GridWorld + tabular Q-learning + trajectory animations
This review examines the evolution of artificial intelligence (AI) and its growing impact across various industries. It highlights key moments in AI's development, real-world applications, and case studies that showcase its role in enhancing efficiency, decision-making, and innovation.
The revolutionary potential of blockchain technology is investigated in relation to elections in this review research. It looks at the Blockchain-Based Election Conducting and Management System (BCECMS) to improve election security and transparency. The study provides important information on the challenges that traditional voting systems face and discusses how blockchain technology will revolutionise voting, allowing for a detailed investigation of the BCECMS with its fundamental components including voting, results verification, voter registration, and authentication.
My research interests span across machine learning, natural language processing, and autonomous systems. I've contributed to various research projects including AI-driven interview systems, sentiment analysis models, and autonomous driving algorithms. I'm particularly interested in the intersection of reinforcement learning and real-world applications.