Surbhi Kapoor
Worcester
Summary
Data Scientist with 6+ years of experience applying machine learning and NLP techniques to automate document workflows at scale. Proficient in Python and SQL, with hands-on experience developing classifiers, fine-tuning LLMs, and building scalable ML pipelines. Currently pursuing a Master's degree in Data Science at WPI to further specialize in data-driven innovation at the intersection of technology and healthcare.
Overview
8
8
years of professional experience
1
1
Certification
Work History
Data Scientist
Ottimate
Oakland
08.2018 - 04.2024
- Developed machine learning and natural language processing pipelines, boosting daily throughput by over 15% in automated classification.
- Fine-tuned transformer models such as BERT and LayoutLMv3 for document layout understanding and labeling.
- Engineered duplicate detection models using LSH indexing, reducing duplication errors from 7% to under 1%.
- Automated data labeling workflows, achieving confidence scores exceeding 0.95 on over 70% of entries.
- Optimized SQL queries for analytics dashboards and model training datasets.
- Collaborated with product and engineering teams to implement machine learning research into production features.
- Participated in team meetings to discuss strategies for improvement.
Course Mentor, Online Math Courses
University of Illinois at Urbana-Champaign
Urbana
01.2016 - 01.2018
- Mentored students in Calculus II and Differential Equations in the university's online program
- Provided conceptual guidance, answered technical questions, and graded coursework for enrolled students
Education
Master of Science - Data Science
Worcester Polytechnic Institute
Worcester, MA05.2027
Bachelor of Science - Mathematics
University of Illinois at Urbana-Champaign
Urbana, IL05.2018
Skills
- Python
- SQL
- Scikit-learn
- BERT
- LayoutLMv3
- Pandas
- Natural language processing
- NumPy
- Git
- Data visualization
- Jupyter
- AWS
- PostgreSQL
- Agile Methodology
- Data Warehousing
Certification
- Machine Learning, Stanford University - Coursera
- Scientific Computing with Python, freeCodeCamp
- SQL for Data Science, LinkedIn Learning
- Applied Machine Learning, LinkedIn Learning
- Time Series Forecasting, LinkedIn Learning
- Data Science Career Paths, LinkedIn Learning
Timeline
Data Scientist
Ottimate
08.2018 - 04.2024
Course Mentor, Online Math Courses
University of Illinois at Urbana-Champaign
01.2016 - 01.2018
Master of Science - Data Science
Worcester Polytechnic Institute
Bachelor of Science - Mathematics
University of Illinois at Urbana-Champaign
Similar Profiles
Courtney CornetteCourtney Cornette
Vendor Retention Specialist at OttimateVendor Retention Specialist at Ottimate
Nick SnyderNick Snyder
Sales Development Representative at OttimateSales Development Representative at Ottimate
Brian SufalkoBrian Sufalko
Director of Sales Development at OttimateDirector of Sales Development at Ottimate