AI Researcher | Machine Learning Engineer | Human-AI Interaction Enthusiast

🚀 Passionate about AI-driven behavioral modeling, multimodal learning, and human-computer interaction, I specialize in machine learning, reinforcement learning, and AI applications in AR/VR. My work focuses on building AI-powered tools for behavioral analysis, human-agent collaboration, and interactive experiences.

• AI-driven AR/VR simulations and player behavior analysis
• AI for emotion-aware computing and multimodal learning (audio, video, text)
• Generative AI & LLMs for code analysis and autonomous agents
• Reinforcement learning applied to human-agent collaboration

🔹 Developed an AI model for recognizing human emotions from physiological and behavioral signals in VR environments.

🔹 Used EEG, eye-tracking, and reinforcement learning to adapt virtual scenarios based on user state.

🔹 Tech: Unity, Python, PyTorch, TensorFlow

• Granger Leadership in a Novel Dyadic Search Paradigm
• Using Multi-Modal Physiological Markers and Latent States to Understand Team Performance and Collaboration
• Latent State Synchronization in Dyadic Partners using EEG
• Decoding neural activity to assess individual latent state in ecologically valid contexts

🔹 Created machine learning models to analyze team dynamics, integrating speech, video, and physiological data for real-time insights.

🔹 Used deep learning, NLP, and computer vision to study human interactions.

🔹 Tech: Python, Hugging Face, TensorFlow, Pandas, SciPy

• Granger Leadership in a Novel Dyadic Search Paradigm
• Hierarchical Multi-Agent Reinforcement Learning with Explainable Decision Support for Human-Robot Teams

🔹 AI-powered chatbot that analyzes codebases, extracts key functions, and generates insightful recommendations.

🔹 Uses LLMs, embeddings, and FAISS-based retrieval for efficient search.

🔹 Tech: Python, Flask, FAISS, PyTorch, OpenAI API, Ollama

🔹 Developed neuromodulation techniques to restore motor function, using dorsal root ganglia (DRG) microstimulation to evoke postural responses and closed-loop neuromuscular stimulation for grasp force control.

🔹 Investigated somatosensory feedback restoration through microstimulation and designed a wearable textile-based electrode system to regulate precise finger movements in individuals with quadriplegia.

🔹 Tech: Python, MATLAB, Signal Processing, Neural Interfaces, Closed-Loop Control

• Closed-loop neuromuscular electrical stimulation using feedforward-feedback control and textile electrodes to regulate grasp force in quadriplegia
• DRG microstimulation evokes postural responses in awake, standing felines

💻 Programming: Python, C++, C#, MATLAB, R, Linux, Git

📊 Machine Learning: PyTorch, TensorFlow, Scikit-learn, OpenCV, Hugging Face

🕶️ AR/VR & Simulation: Unity, Unreal Engine, Reinforcement Learning

🎧 Multimodal AI: Speech & Audio Processing, Emotion Recognition, Video Analysis

If you're interested in AI, reinforcement learning, multimodal ML, or AR/VR research, let's connect!

👉 LinkedIn | 📫 [email protected]