Profile

Research & Engineering Overview

Research depth

LLM fairness, reasoning-time bias, hallucination mitigation, robust NLP, stance detection, and human-centered evaluation.

Applied AI systems

RAG, multi-agent LLM workflows, LLM-as-a-judge evaluation, synthetic QA generation, and uncertainty-aware model assessment.

Engineering execution

Python ML pipelines, PyTorch/Hugging Face experimentation, cloud deployment, backend prototypes, full-stack product builds, and high-quality agentic coding workflows.

Research Direction

My work focuses on trustworthy AI, NLP/LLM research, applied science, model evaluation, and AI safety / reliability. I translate ambiguous AI quality questions into measurable evaluation protocols, then use those signals to improve models and systems.

I have worked as a research assistant at the DHS Center for Accelerating Operational Efficiency (CAOE) and the Data Mining and Machine Learning (DMML) Lab, advised by Dr. Huan Liu and Dr. Mickey Mancenido. I previously earned my B.S. and M.E. at Korea University, where I was advised by Dr. Jaewoo Kang.

Experience

Applied Scientist Intern, Amazon — Bellevue, WA · Fall 2025
AI/ML Intern, AMD — Austin, TX · Summer 2025
SDE Intern, AMD — Austin, TX · Fall 2024
Research Assistant, DHS-CAOE — Tempe, AZ · 2022 – 2025
Research Assistant, ONR — Tempe, AZ · 2021 – 2022
Research Assistant, Korea University DMIS Lab — Seoul, KR · 2017 – 2019

Technical Strengths

Research Areas

Trustworthy AI Fairness and bias mitigation Hallucination evaluation Robust NLP Human-centered AI Model reliability

LLM Systems

RAG Vector DBs Weaviate Chroma Faiss LLM-as-a-judge Synthetic QA generation Multi-agent LLM Prompt engineering Inference-time scaling

ML & DL

PyTorch TensorFlow Hugging Face Transformers PEFT Accelerate Datasets Pandas NumPy

Fine-tuning

Supervised fine-tuning SFT Classification Forecasting RLHF Parameter-efficient methods LoRA P-tuning

Engineering

Python SQL JavaScript Flask Streamlit Node.js Docker Git Linux CI/CD workflows

Cloud & MLOps

AWS SageMaker S3 Redshift Glue Lambda CodeBuild GCP Model serving Inference optimization WandB MLflow

Models

Claude GPT-4o Llama-3 Mistral DeepSeek BERT T5

Methods

Bayesian inference Uncertainty quantification Statistical analysis Human-subject study design Jupyter

Where I Can Contribute

Applied Scientist / Research Scientist: trustworthy LLMs, NLP, model evaluation, fairness, hallucination mitigation, and AI reliability.
ML Engineer / AI Engineer: evaluation infrastructure, RAG and LLM systems, Python ML pipelines, cloud-backed prototypes, and production-oriented AI workflows.
Cross-functional AI teams: translating open-ended research questions into measurable product and system improvements.

Claire Kim