Ediz Ertekin Jr.
Current Status: Building
Thank you for stopping by, I hope you enjoy exploring my personal portfolio. Feel free to reach out to me if you have any questions.
About Me
Hello! I would like to share a little about myself. My name is
Ediz Ertekin Jr., I am a recent graduate from UC Berkeley with a
Bachelor's degree in Computer Science and a minor in Data Science.
I am passionate about the intersection of technology and
mathematics, which inspired my academic journey and continues to
fuel my interest in exploring opportunities various fields
including machine learning, software development, and computer
vision.
In my free time, I enjoy practicing piano—a few of my favorite
pieces include Moonlight Sonata, River Flows in You, and
Dandelions by Ruth B. I also enjoy reading; currently, I'm reading
Deep Work by Cal Newport. Some of my all-time favorites include
Start with Why by Simon Sinek, Ready Player One by Ernest Cline,
and Zero to One by Peter Thiel. Additionally, I love traveling and
spending time outdoors, engaging in activities like hiking,
running, snowboarding, and cycling. If you are interested, click
the button below to view some of my photos from my travels.
Coursework
- Computer Science
- CS 61A: Structure and Interpretation of Computer Programs
- CS 61B: Data Structures
- CS 61C: Machine Structures
- CS 70: Discrete Mathematics and Probability Theory
- CS 161: Computer Security
- CS 162: Operating Systems and System Programming
- CS 170: Algorithms and Intractable Problems
- CS 198: Competitive Programming
- Machine Learning
- CS 180: Computer Vision
- CS 189: Introduction to Machine Learning
- EECS 127: Optimization Models in Engineering
- Mathematics
- Math 1A: Calculus I
- Math 1B: Calculus II
- Math 53: Multivariable Calculus
- Math 54: Linear Algebra and Differential Equations
- Math 55: Discrete Mathematics
- Physics
- Physics 7A: Physics for Scientists and Engineers
- Physics 7B: Physics for Scientists and Engineers
- Data Science
- DATA 8: Foundations of Data Science
- DATA 100: Principles and Techniques of Data Science
- Data 104: Ethics of Data Science
- Entrepreneurship
- Engin 183A: Richard Newton Lecture Series
- Engin 183E: Technology Entrepreneurship
Projects
- Course Projects
- Augmented Reality (Python, OpenCV) cs180
- Facial Keypoint Detection (PyTorch) cs180
- Diffusion Models from Scratch! (PyTorch) cs180
- Housing Appraisal GLM (Pandas) data100
- Spam Filter (scikit-learn) data100
- World Exploration Game (Java) 61b
- Deque API (Java) 61b
- Scheme Interpreter (Python, Scheme) 61a
- Ants vs. SomeBees (Python) 61a Code available upon request for course projects.
- Personal Projects
- Neural Network From Scratch (NumPy)
- Deep Learning on MNIST (PyTorch)
- AI Chatbot (Python, JS, Tailwind)
Research
JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models
The use of Large Language Models (LLMs) in hiring has led to legislative actions to protect vulnerable demographic groups. This paper presents a novel framework for benchmarking hierarchical gender hiring bias in Large Language Models (LLMs) for resume scoring, revealing significant issues of reverse gender hiring bias and overdebiasing.
SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration
The development of unbiased large language models is widely recognized as crucial, yet existing benchmarks fall short in detecting biases due to limited scope, contamination, and lack of a fairness baseline. SAGED(bias) is the first holistic benchmarking pipeline to address these problems. The pipeline encompasses five core stages: scraping materials, assembling benchmarks, generating responses, extracting numeric features, and diagnosing with disparity metrics.
Experience
Undergraduate ML Researcher
Holistic AI | April 2024 - Present
- Conducted research on mitigating gender hiring biases in Large Language Models (LLMs) used for resume scoring
- Developed a benchmarking framework to evaluate gender biases like Level, Spread, Taste-based, and Statistical bias using anonymized resume data
- Implemented counterfactual metrics for hiring bias, such as Rank After Scoring (RAS), Impact Ratio, and Permutation Test-Based Metrics
- Analyzed data across 10 LLMs, identifying male biases in certain industries and created visualizations to highlight bias patterns, aiding interpretation
Software Engineering Intern
Harness io | May 2024 - Aug 2024
- Built a data platform by implementing Apache Kafka for seamless connectivity between MongoDB and AlloyDB
- Leveraged PostgreSQL and SQLMesh for real-time data filtering, and deployed a Cube API semantic layer
- Designed a Harness marketplace MVP, creating a Command Line Interface (CLI) to streamline the generation of custom plugins,improving customer experience and workflow efficiency by 50%
Machine Learning Engineer
Nexa Speech | Jan 2024 - May 2024
- Contributed to the development of a machine learning system for multi-agent conversations, leveraging Wisper, FastAPI, and ElevenLabs to build a robust speech-to-speech pipeline
- Fine-tuned agent interactions using RAG and prompt engineering based on user feedback
- Presented my work at the Data Science Discovery Program Symposium
Software Engineering Intern
Snaplogic | May 2023 - Aug 2023
- Developed a new library for SnapGPT, an AI-powered platform for automating data integration pipelines across cloud data warehouses, leveraging NLP pratices and a RAG infrastructure
- Engineered a module to support premium integrations, enhancing the platform's capabilities for complex scenarios
- Developed algorithms for seamless data migration across cloud solutions, optimizing efficiency, and reliability
- Implemented tests for validation efforts to ensure accuracy and stability of integration pipelines, driving platform
Photography
Japan
California
