Open to opportunities

Baolin Liu

@baolinliu

Message

Senior Data Scientist specializing in NLP and Computer Vision.

United States

Message

What I'm looking for

I am looking for a role that fosters innovation, collaboration, and continuous learning.

I am a Senior Data Scientist based in the San Francisco Bay Area, with extensive experience in creating automated scripts, machine learning models, deep learning, and statistics. My expertise lies in integrating machine learning solutions end-to-end in the cloud using Python, with a particular focus on Natural Language Processing (NLP) and Computer Vision.

Throughout my career, I have successfully trained and deployed various models, achieving high accuracy rates in diverse applications. I thrive in small team environments, where I can wear multiple hats and leverage my resourcefulness to deliver quick turnarounds from idea to deployment. My recent projects include fine-tuning large language models for semantic search and developing custom classification models that have significantly improved operational efficiencies.

Experience

Work history, roles, and key accomplishments

Current

Senior (Full Stack) Data Scientist

Current

Signal Mine

Mar 2024 - Present (1 year 4 months)

Trained, deployed, and monitored custom models in Vertex AI for online and batch predictions, migrating from Wandb. Developed and fine-tuned LLMs for custom token classification, multi-label models, and semantic search to standardize food descriptions and improve search results.

Vertex AI W&B Fine Tuned LLMs fastAPI Gradio Claude API NLP Computer Vision Python Claude APIs

Senior Data Scientist

REI Systems

Mar 2023 - Present (2 years 4 months)

Trained and deployed a 30-category IT classifier with 96% accuracy in AWS Lambda. Conducted web scraping using Selenium, BeautifulSoup4, and Requests to build new datasets.

AWS Lambda Selenium LLMs)CUDA Vector Databases RAG

Senior Data Scientist

CoreLogic

Aug 2022 - Present (2 years 11 months)

Retrained and deployed a forecast model to predict mortgage interest rates in GCP. Utilized derived methods to fill information in data.

GCP Forecast Modelling Data Derivation Machine Learning Python

Senior Data Scientist

PennyMac

Mar 2021 - Present (4 years 4 months)

Built a multi-class text classifier to identify over 300 mortgage documents with 95% accuracy in AWS SageMaker. Developed monitoring systems to track model performance and optimized labels and sample sizes for best accuracy.

AWS Sagemaker Text Classification Systems Model Monitoring Data Labeling Machine Learning Python

Data Science Mentor

Thinkful

Dec 2018 - Present (6 years 7 months)

Hosted weekly meetings with Thinkful students for the Data Science curriculum. Reviewed take-home exams and provided interview preparation.

Mentoring Interview Preparation

Data Scientist

SpringML

Jan 2018 - Present (7 years 6 months)

Developed custom object detection models, image classification models, and NLP models for various projects. Applied pre-trained solutions and rapid prototyped POCs as a GCP Partner for Fortune 100 companies.

Object Detection NLP CNN AutoML Word2Vec NER GCP

Data Science Intern

Data RPM

May 2017 - Present (8 years 2 months)

Researched LSTM Networks for Time Series Data in TensorFlow in Azure. Investigated visualization tools for sensor data in D3.

LSTM Networks Time Series Analysis TensorFlow Azure D3.Js Data Visualization

Data Science Intern

Bridge US

Jul 2016 - Present (9 years)

Collected PDF data and trained and deployed classifiers to identify 30 different immigration documents with 90% accuracy in AWS EC2.

Document Classification AWS EC2 Machine Learning Python

Education

Degrees, certifications, and relevant coursework

The University of New Haven

Master of Science, Data Science

2015 - 2016

Pursued a Master of Science degree focusing on advanced data analysis techniques. Gained expertise in machine learning, statistical modeling, and data visualization.

San Jose State University

Bachelor of Science, Civil Engineering

2004 - 2009

Completed a Bachelor of Science in Civil Engineering, covering principles of structural design, transportation, and environmental engineering. Developed foundational knowledge in engineering mechanics and materials.