Agam Iheanyi-Igwe
CS student at Stanford, passionate about mitigating
algorithmic bias and building impactful software.
Education
Stanford University
Bachelor's degree, Computer Science (2023 - 2027)
Grade: 3.84/4.0
Activities: Society of Black Scientists and Engineers + Black in CS (Co-President)
- CS161 - Algorithms
- CS107 - Computer Organization & Systems
- CS109 - Probability
- CS106B - Data Structures and Algorithms
- CS103 - Discrete Math
- CS124 - NLP
- CS111 - Operating Systems
- CS29N - Computational Decision Making
Howard Community College
Associates Degree in STEM Studies (Dec 2019 - June 2023)
GPA: 3.89/4.0
Experience
SWE Intern
Jun 2025 - Present
Stanford University Department of Computer Science
Undergraduate Teaching Assistant
Mar 2025 - Present · Part-time
- Teach weekly sections for Stanford undergrads in Python/C++ for Stanford's intro data structures and algorithms class.
- Conducted office hours to provide student support and grading for coding assignments and exams.
Burton Algorithms
Software Engineer
Mar 2025 - Present · Contract
- Developing backend infrastructure for startups—taking projects from concept to production across a wide range of industries.
- Specialized in AWS Lambda and Systems Design.
Skill Inventory
Lv. Intermediate
Lv. Advanced
Lv. Intermediate
Lv. Beginner
Projects
TreePath (Winter 2025)
Featured
- Designed and implemented a web app with Node.js, Express.js, MySQL, React, and TailwindCSS, providing Stanford CS students a user-friendly interface for tracking course progress and requirements.
- Integrated a BeautifulSoup web-scraping pipeline to extract Stanford course data and descriptions.
- Implemented a collaborative filtering algorithm to recommend courses based on similar user academic history.
Multi-Source Dataset Retrieval System (Autumn 2024)
AI/ML
- Developed a multi-repository search algorithm, utilizing OpenAI API, MongoDB, and web scraping to efficiently filter and retrieve relevant datasets from OpenML, Kaggle, and UCI repositories.
- Provided ML developers with quick, easy access to diverse training data, promoting fairness by exposing models to broader ranges of data.