Hanzi Xu

AI Researcher

Menlo Park, California, United States1 yr 10 mos experience

Key Highlights

Expert in NLP and multi-modal learning.
Proven track record in deploying deep learning models.
Strong academic background with a PhD in Computer Science.

Stackforce AI infers this person is a Healthcare and Entertainment-focused NLP and Machine Learning expert.

Contact

Skills

Core Skills

NlpDeep LearningAutomationMultimodal LearningMachine Learning

Other Skills

Model Fine-tuningXGBoostMultimodal ModelsContent RepresentationTagging PredictionStatistical ModelingSentiment AnalysisData AnalysisStatisticsMatlabSQLRPython (Programming Language)SAS

Experience

1 yr 10 mos

Total Experience

1 yr 10 mos

Average Tenure

1 yr 10 mos

Current Experience

Netflix

2 roles

Research Scientist

Jul 2024 – Present · 1 yr 10 mos · San Francisco Bay Area

Machine Learning Research Intern

Jun 2023 – Aug 2023 · 2 mos · Los Gatos, California, United States · On-site

Developed a deep content representation model by utilizing in-house multimodal models, integrating audio, video, and
text assets, and performed downstream tagging prediction tasks
Categorized and scored content for genre and subgenre tags, achieving 95% AUC score and 98% accuracy in practice
Integrated the designed model in the production and internal tools for various use cases, such as aiding human experts
in annotation, defining audience “fan club” categories, and selecting titles for Netflix collections

Deep LearningMultimodal ModelsContent RepresentationTagging PredictionMultimodal Learning

Penn mutual

NLP Research Collaborator

Jun 2022 – Jul 2024 · 2 yrs 1 mo · Philadelphia, Pennsylvania, United States

Deployed attention-based deep learning models on health care surveys and attending physician statement classifications
Fine tuned G PT and Llama 2 models for summarizing and categorizing medical records, automating the review process
Designed an XGBoost classification model to automate the decision-making process for insurance providers, reducing the workload of human experts by 25%

Deep LearningNLPModel Fine-tuningXGBoostAutomation

Temple university

Research Assistant

Jan 2020 – Jul 2024 · 4 yrs 6 mos · Philadelphia, PA

Protagolabs

Machine Learning Researcher

Jun 2019 – Dec 2019 · 6 mos · Vienna, Virginia, United States

Applied machine learning and statistical modeling techniques to develop and evaluate Natural Language Processing (NLP) methods, improving Chatbot performance
Designed an out-of-domain input detector, utilized an AutoEncoder for more precise feature representations
Conducted sentiment analysis and vulgar language detection on out-of-domain messages using LSTM architecture with attention mechanism

Machine LearningStatistical ModelingNLPSentiment Analysis