Completed Worked on skill routing and planning models for an automotive AI assistant, including training data preparation, difficulty-based training pools, and targeted post-training for dashboard warning light scenarios.
View Details →Projects
Selected work in large language models, AI agents, and scientific machine learning.
Completed 
Completed Developed AROnet, a discrete neural operator for transient Darcy flows, and paired it with latent-space adaptive sampling to improve predictions when simulation data is limited.
View Details →
Completed Developed a conversational AI agent for cloud operations using MCP and Kubernetes. Worked on semantic tool retrieval, task planning, and retrieval-augmented answers to reduce context usage and improve response accuracy.
View Details →
Completed Built chain-of-thought training data for math problems, fine-tuned Qwen2-7B with LoRA, and evaluated reasoning quality with an automated semantic matching pipeline.
View Details →