cv

SWE-Agentic AI Master's Intern

Honeywell

• Built agentic evaluation judge framework across task completion, context retention, and error recovery scenarios
• Routed LLM inference across Anthropic and OpenAI via OpenAI-compatible layer; built FastAPI-backed data visualizer
• Dockerized and deployed eval pipeline; integrated Databricks model-serving endpoints, tracking per-call cost and latency

Graduate Research Assistant

USC Machine Learning Center

• RaMem: Contextual Reinstatement for Long-Term Agentic Memory
• Built RAG-based agentic memory pipeline enabling LLM agents to recall evidence across multi-session conversations
• Engineered temporal evidence filtering with session metadata to remove semantically related but invalid memories
• Implemented hybrid retrieval with Reciprocal Rank Fusion (RRF) over semantic search and BM25, improving F1 by 11.6 points across GPT-4o, GPT-4.1-mini, and Qwen3-8B
• Reduced prompt context length by 50% while preserving performance against state-of-the-art agent memory baselines
• Student-Job Recommendation System
• Led end-to-end development as 1st author, mentoring 2 Master’s students and collaborating with PhD candidates
• Tackled cold-start scenarios using synthetic explanation generation via GPT-4o-mini distillation into Llama-3-8B-Instruct for student-teacher learning
• Implemented multi-step fine-tuning via dual optimization framework with LoRA, jointly training 2 objectives for ranking (InfoNCE contrastive loss)
• Achieved up to 2.6× (Recall@5) and over 3× (NDCG@5) improvement over LLM baselines

Research Associate

Bruker

• Developed custom Python pipelines to automate experimental data analysis, adapting to evolving scientific demands
• Designed interactive Plotly dashboards to visualize complex biological datasets, enabling faster data-driven insights

Process Engineer

Applied Materials

• Launched Lab Inventory Database, delivering full workflow traceability and reducing processing time by 80%
• Built automated data visualization pipelines using Pandas and Plotly to extract insights from terabyte-sized datasets

Master of Science

University of Southern California

Computer Science

• Algorithms, Machine Learning, Natural Language Processing, Trustworthy LLMs, Hardware for ML

RaMem: Contextual Reinstatement for Long-Term Agentic Memory

arXiv

Yang, W., Kan, B., et al.

De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models

arXiv

Kan, B., et al.

A locus coeruleus to dentate gyrus noradrenergic circuit modulates aversive contextual processing

Neuron

Seo, D.-O., Zhang, E. T., Piantadosi, S. C., Marcus, D. J., Motard, L. E., Kan, B. K., et al.