Abby Seseri
M.S. in Computer Science at UCLA
I'm currently getting my M.S. in Computer Science at UCLA, and I have a passion for building complete, data-driven applications. My experience ranges from developing full-stack systems and secure networking protocols to implementing deep learning models. In my free time, I combine my love for sports and tech by working on projects like my WNBA analytics platform, but I also enjoy going outdoors to hike or spend time on the beach.
Education
University of California, Los Angeles
Master of Science | 2025-2026 (Expected)
Major: Computer Science
Relevant Courses: Big Data Analytics, Neural Signal Processing, Advanced Software Engineering
University of California, Los Angeles
Bachelor's Degree | 2022-2025
Major: Computer Science
Awards: Dean's Honors List (Winter 2023, Spring 2023)
Relevant Courses: Machine Learning, Advanced Neural Networks & Deep Learning, Data Science, Artificial Intelligence, Data Mining, Data Management Systems, Operating Systems, Algorithms & Complexity, Web Applications, Computer Networks, Software Engineering
Santiago Canyon College
Community College Credits | 2018-2022
Villa Park High School
High School Degree | 2018-2022
Awards: Summa Cum Laude
Experience
Teaching Assistant (COM SCI M152A)
UCLA Computer Science Department | Fall 2025
Leading weekly lab sections for the Digital Design Laboratory course. Mentoring teams of students on digital logic concepts and hardware description with Verilog. Grading lab assignments and providing constructive feedback to help students master the material.
AI Data Specialist (Contractor)
Data Annotation | Summer 2024
Enhanced large language models (LLMs) using Reinforcement Learning from Human Feedback (RLHF). Evaluated model outputs for safety, accuracy, and adherence to complex guidelines, and performed quality assurance on the work of other analysts.
Leadership & Activities
Upsilon Pi Epsilon, UCLA
Member & Tutor | 2023-2025
Inducted into the international honor society for computing, open to the top third of CS students. Provide tutoring and mentorship to peers in foundational computer science courses.
Projects
Predicting Text from Intracranial Neural Signals
Optimized a GRU-based Brain-Computer Interface (BCI) decoder to predict text from neural signals using PyTorch. Implemented advanced regularization techniques, AdamW optimization, and time-masking augmentation to reduce overfitting. Achieved a Phoneme Error Rate (PER) of 18.37%, representing a 16.4% improvement over the baseline model.
WNBA Analytics Web Application
Built a full-stack WNBA analytics platform featuring a custom Scikit-learn model to find statistically similar players. The entire application is containerized with Docker and includes a CI/CD pipeline with GitHub Actions for automated testing.
AgentSociety: User Behavior Simulation Agent
Developed an LLM-based agent to simulate realistic user behavior using Chain-of-Thought reasoning and Iterative RAG. Implemented a modular architecture with smart context selection and user persona extraction to strictly enforce writing styles. Achieved a 5.06% improvement in review generation quality compared to the competition baseline.
EMG Keystroke Prediction (emg2qwerty)
Developed an LSTM-based deep learning model to predict keyboard strokes from sEMG muscle signals. Experimented with various RNN architectures and preprocessing techniques to improve Character Error Rate (CER) by 7%.
Reliable, Secure Network Communication System
Developed a reliable, encrypted bidirectional data transfer protocol over UDP. Implemented AES-256 encryption, HMAC for authentication, and ECDSA/Diffie-Hellman for secure key exchange. Ensured data integrity and confidentiality using TLS-like handshakes and cryptographic standards.
HTTP Server and CRUD API
Engineered a multi-threaded HTTP 1.1 server in C++ supporting static resource serving and a JSON-based REST API. Designed a modular RequestHandler architecture using Boost.Asio and implemented a production-grade build pipeline with CMake, Docker, and GoogleTest for automated coverage and integration testing.
Personal Website
Developed a personal website that is hosted on github pages using html, css, and javascript.
Brewin Language Interpreter
Created an interpreter for a language called Brewin supporting typical arithmetic and comparison operators, dynamically-scoped variables, first-class functions, lambdas, pass-by-reference and pass-by-value, limited type coercions, objects and all operations on objects, and prototypal inheritance using an abstract syntax tree.
Peach Party Game
Constructed a 2-player game where characters and 2 enemy types move along a 16x16 grid following different algorithms and possess states depending on 6 square types on the grid, competing for the most coins in 1 minute.