FlowCV Logo
Skills
Languages: Python, SQL, R, Excel, Matlab
Tools: AWS, BigQuery, Databricks, Docker, Git, Langchain, Power BI, PostgreSQL, PySpark, Spark SQL, Spotfire, Tableau
Statistics: Hypothesis & A/B Tests, Regression, Classification
ML: Deep Learning, Gen AI, k-means, Neural Networks, PCA, RAG Pipelines, Random Forest, XGBoost, Clustering
Relevant Experience
Data Scientist, Upwork
02/2023 – present | Remote
  • •Developed a RAG-based system on AWS using Bedrock and Sagemaker that automated document and image parsing and enabled natural language question answering, reducing query response time by 40%
  • •Built a data pipeline utilizing AWS Lambda, Textract, S3, and Bedrock (Cohere Embed V3) to store and retrieve vector embeddings in DocumentDB, supporting semantic NLP responses with Bedrock (Claude V3 LLM)
  • •Applied anomaly detection techniques (graph analysis, k-means, DBSCAN, & hierarchical clustering) and PySpark on AWS Sagemaker, NumPy, & SciPy to identify fraudulent overcharging in 16,000 vehicle service records, visualizing results with Matplotlib, Streamlit, & Tableau and achieving 30% cost savings
    • Data Consultant, Catenactio
    05/2024 – 09/2024 | Los Angeles, CA
  • •Developed an HR chatbot powered by Generative AI (Gemini API) on Google Cloud Platform, reducing repetitive inquiries by 40% and cutting HR operational costs by 25% through optimized synthetic training data
  • •Architected automated data pipelines using Python and SQL, enabling real-time cybersecurity threat detection and a 30% reduction in response times
  • •Delivered high-impact analytics solutions by collaborating with cross-functional stakeholders, driving a 20% increase in operational efficiency and accelerating business growth
    • Operations Manager, Beverly Hills Arthritis Associates
    11/2021 – 11/2022 | Beverly Hills, CA
  • •Spearheaded the development of an automated data cleaning pipeline using Excel and Python scripts, boosting efficiency by 60% and uncovering $100,000 in profit from unpaid accounts within 6 months
  • •Implemented a new Epic EHR data documentation system, reducing errors by 15% and ensuring accuracy in over 1,000 patient records, potentially improving patient care through enhanced data quality
  • •Directed a team of analysts to process insurance claims, ensuring efficient management of over 120 complex med-legal cases
    • Research Associate II, Cedars-Sinai (Smidt Heart Institute)
    03/2021 – 10/2021 | Los Angeles, CA
  • •Improved data collection and analysis with 3 custom Excel templates, reducing data processing time by 80%
  • •Applied advanced statistical techniques in Python, including correlation analysis and regression modeling, to quantify gene-protein associations, contributing to a 30% improvement in experimental reproducibility and validation
    • Associate Scientist, Amgen
    07/2019 – 01/2021 | Thousand Oaks, CA
  • •Developed an end-to-end system that automated Amgen's workflow by integrating Biovia ELN for assay templating and generating Spotfire reports, reducing analysis time and resource use by 50%, which earned VP recognition and a promotion to project lead
  • •Authored technical reports documenting methodologies and findings, supporting regulatory submissions and internal reviews
  • •Oversaw the development of 9 drugs from discovery to FDA approval and eventual market release
    • Projects
  • •Visualized mental health trends in 300,000 patient records using Tableau and Python, revealing key intervention areas, including that 54% of struggling students are US males
  • •Built a 98% accurate XGBoost model that classifies susceptibility to mental health difficulties as low, medium, and high
  • •Engineered an employee churn model (XGBoost - 98% accuracy & precision) using Python that identified 5 key factors in employee turnover and projected a 20% improvement in resource management and employee satisfaction
  • •Analyzed a 5-year employee dataset using Pandas, Seaborn, & Tableau to uncover insights and identify a strong correlation between assigning > 4 projects and a 200% surge in employee attrition
    • Certificates
    Google Advanced Data Analytics
    IBM Data Science
    AI/ML in Precision Medicine (Stanford Med)
    Data Science in Healthcare
    Education
    Bachelor of Science, University of California San Diego
    09/2014 – 06/2018 | La Jolla, CA

    Majors: Cognitive Science (Machine Learning & Neural Computation) | Biochemistry & Cell Biology