
Applied ML researcher and engineer with experience building production ML systems, LLM-based applications, retrieval-augmented pipelines, and scalable data-driven workflows. Strong hands-on background in Python, SQL, PyTorch, AWS, ranking systems, MLOps, and multimodal generative modeling, with research interests in interpretable AI, diffusion models, and enterprise GenAI systems. Currently pursuing a PhD focused on Generative AI and LLMs, following completion of a Master’s degree.
Machine learning
Supervised learning
Basic neural networks
Machine learning frameworks
LLM applications
Data analysis
Data preprocessing
Data modeling
Data systems
Programming languages: Python, SQL, Java
LLM-Assisted Multimodal Personality Interpretation
• Prototyped an LLM-assisted framework to interpret personality-related cues from structured multimodal signals, including facial action units, gaze, head motion, and speech features.
• Used retrieval over semantically organized behavioral descriptors with prompt-based reasoning to generate interpretable personality summaries.
• Demonstrates experience in LLM workflows, retrieval-based reasoning, and interpretable multimodal analysis.
Semantic Personality Dataset and Controllable Facial Expression Generation
• Built a semantically interpretable dataset combining FACS Action Units, gaze, and head motion with Five-Factor personality annotations.
• Developed an attention-based diffusion model for controllable facial expression generation using speech and personality traits, achieving an FID of 0.6 and an R² of 0.77.
• Demonstrates strength in multimodal learning, generative AI, and quantitative model evaluation.
Multi-Modal GNN for Personality Trait Prediction
• Developed a graph neural network to fuse multimodal behavioral signals for personality trait prediction, achieving 93% accuracy.
• Applied attention mechanisms to improve interpretability across heterogeneous input features.
• Demonstrates experience in multimodal representation learning, predictive modeling, and applied AI system design.