CURATED STYLES:
🌌 AURORA INTELLIGENCE · 2026 ENGAGEMENTS

Aryan Gupta. Fluid Intelligence in Motion.

AI & Reinforcement Learning Engineer. Designing emergent multi-agent self-play systems, deep computer vision, and cryptographic steganography.

30M+PPO Steps Simulated
95%Seeker Win Rate
MeitYGovt Research Fellow
IBM CloudCertified Deployment
OVERVIEW

Harmonizing Complexity with Luminous Clarity.

Autonomous Agents (PPO/MADDPG)

Self-play multi-agent dynamics with continuous Pymunk physics, GPU parallelization, and reward engineering.

Computer Vision & Security

Aesthetic steganographic QR codes using Stable Diffusion and ControlNet with distance-authenticated cryptographic signatures.

Cloud & Predictive AI

Enterprise time-series forecasting (ARIMA) deployed to auto-scaling IBM Cloud environments.

EXPERIENCE

Research Fellowships & Leadership.

Ministry of Electronics and Information Technology (MeitY)

Jun 2025 – Jul 2025

AI and Security Research Intern

Pioneered generative error-corrected QR steganography using Stable Diffusion and ControlNet for defensive covert communications.

Edunet Foundation in collaboration with IBM

Jul 2024 – Aug 2024

AI and Cloud Intern

Engineered predictive ARIMA time-series models and deployed REST endpoints on IBM Cloud infrastructure.

ACM MUJ Student Chapter

Aug 2023 – Present

Head of Projects and Research Team

Directed 15+ student developers selected from 40+ applicants, maintaining a 90% project completion benchmark.

PROJECTS

Selected Implementations.

MARL Tag: 3v3 Pursuit-Evasion

PyTorch self-play reinforcement learning system utilizing PPO with GAE. Parallelized over 8 CUDA environments (30M steps) with 102-ray perception and 95% victory rate.

PyTorchCUDAPPOPymunk

Multi-Agent Fleet Transit Optimizer

Autonomous taxi simulation combining MADDPG with dynamic A* pathfinding. Slashed passenger wait times by 20% across 100+ simulated passengers.

MADDPGA*PyGamePyTorch

Student Performance Diagnostic

Random Forest classifier with 96% accuracy; optimized via GridSearchCV and rigorous data normalization for educational intervention.

scikit-learnRandom ForestGridSearchCV

Automated Video Generation Engine

End-to-end Python pipeline converting structured data into automated video media using MoviePy and REST APIs, reducing manual latency by 90%.

PythonMoviePyAutomation
SKILLS

Technical Matrix.

Languages & Core Systems

Python, C/C++, JavaScript, SQL, CUDA Acceleration, Unix/Linux.

AI & Frameworks

PyTorch, scikit-learn, Keras, NumPy, Pandas, Matplotlib, Pymunk, PyGame.

CONTACT

Connect with Aryan Gupta.

Available for 2026 roles in AI, Machine Learning, and Systems Engineering.