About me

Hi! I am a rising senior at Northwestern University double majoring in Computer Science and Data Science. I love taking complex technical problems / tools and shaping them into clear, accessible solutions for people to use.

My combined background provides a holistic understanding of the technical challenges I tackle. Because I have hands-on experience across the entire lifecycle of a product, from architecting data pipelines and training predictive models to developing dynamic front-end interfaces, I can see the complete picture. This visibility allows me to bridge the gap between raw logic and the final user experience, enabling me to engineer resilient, integrated platforms that provides value to any user.

Core Skills

  • Software Development

    Building full-stack web applications, design/implement dynamic frontend components, and robust backend from the ground up.

  • AI & Machine Learning

    Integrating LLM agents and predictive modeling frameworks to automate research, parsing, and complex system logic.

  • Data Engineering & Analytics

    Architecting scalable data ingestion pipelines and centralizing complex datasets to power dynamic dashboards/data reports, uncover trends, and drive decision-making.

Resume

Education

  1. Northwestern University

    2023 — 2027

    Bachelor of Arts in Data Science | Bachelor of Arts in Computer Science
    Cumulative GPA: 3.99/4.00 | Major GPA: 4.00/4.00 | Dean's List: 9/9 quarters

Experience

  1. Software Engineer — NextTier

    June 2026 — Present
    • Built an AI-driven custom merchandise platform on AWS using React and FastAPI microservices, enabling real-time T-shirt design and ordering workflows through scalable REST APIs.
    • Developed a LangChain-based AI agent orchestration layer with AWS Bedrock and OpenCV, automating multi-step merchandise workflows through prompt optimization and tool-calling capabilities.
    • Implemented a RAG-powered product support assistant using PostgreSQL pgvector and Bedrock embeddings, delivering context-aware responses through semantic search over product knowledge bases.
    • Engineered an asynchronous order processing pipeline with AWS SQS and Redis caching, supporting 10K+ simulated daily orders with a 99% success rate while improving system scalability.

  2. Software Engineer — MyFlexLearning

    March 2026 — Present
    • Engineered an AI-powered academic scheduling platform that generated optimized student schedules from natural language inputs by integrating constraint-solving algorithms and backend automation.
    • Developed dynamic Angular frontend components and integrated OpenAI APIs with prompt engineering techniques to convert user requirements into structured database configurations.
    • Designed a constraint satisfaction engine using Google OR-Tools and customized data pruning algorithms, reducing model search space by 45% while significantly improving backend scheduling efficiency for complex academic requirements.
    • Built API-driven data ingestion and aggregation pipelines with Python and SQL, enabling customer-facing report card generation and supporting 100+ K-12 schools.
    • Optimized scheduling workflows by developing a high-performance assignment engine that generated 3,000+ student schedules in under 30 seconds while supporting flexible user constraints.

  3. Research Associate — Northwestern University/Open Communities

    November 2025 — March 2026
    • Architected a fully containerized Python web application using FastAPI deployed on Railway, automating fair housing analysis across peer modeling and lender profiles.
    • Built centralized data ingestion pipelines utilizing U.S. Census and FDIC APIs, applying Scikit-learn and SciPy to execute predictive machine learning and statistical modeling.
    • Developed an accessible analytics interface for non-technical users, reducing manual analysis time by 90% and enabling five additional data-driven evaluation methodologies.
    • Collaborated with stakeholders across varying levels of technical expertise, translating complex analytical concepts into clear, accessible explanations to support informed decision-making.

  4. Data Engineering Intern — Continental Tires

    June 2025 — August 2025
    • Designed automated ETL pipelines and Power BI dashboards using Python and SQL Server to track attendance KPIs for 2,000+ employees, analyzing workforce trends to flag irregularities and ensure labor compliance.
    • Evaluated time-series data to monitor electricity usage and production costs across 100+ manufacturing machines, identifying operational bottlenecks and delivering insights to drive energy efficiency.
    • Integrated rigorous data validation and cleansing protocols into the ingestion workflows to resolve schema mismatches and handle missing values, ensuring data integrity and downstream pipeline stability.

Projects

  1. HMDA AutoResearch Framework — Northwestern University

    March 2026 — May 2026
    • Architected an AI infrastructure and generative sandbox, enabling data science and fair lending stakeholders to directly generate localized demographic proxy models on HMDA datasets to audit hidden lending biases.
    • Analyzed region-specific financial features (e.g., debt-to-loan ratios) utilizing constrained LLM workflows to resolve geographic target variance and infer applicant demographics.
    • Evaluated predictive models (XGBoost, LightGBM) and LLM agent behavior to ensure accuracy, implementing strict system instructions to prevent data leakage during demographic analysis.
    • Optimized demographic classification accuracy (averaging ~75% across 3-class regional targets) by accelerating the feature analysis lifecycle, reducing analysis iteration time by 70%.

Skills

  • Programming Languages

    Python, SQL, TypeScript, JavaScript, HTML, R, C++

  • Data Analysis & Machine Learning

    NumPy, Pandas, scikit-learn, Matplotlib, Seaborn, Power BI

  • Frameworks & AI

    Angular, FastAPI, LangChain, AWS Bedrock, Google OR-Tools

  • Tools & Infrastructure

    AWS (Lambda, SQS, Bedrock, S3), Docker, CI/CD, Git/GitHub, Databases (PostgreSQL, SQL Server, MongoDB)