RAS (Reliability, Availability, Serviceability) Management | AI Infrastructure Team

Designed and implemented a DRAM Fault Analyzer within the OpenBMC firmware environment, enabling parsing and persistent storage of CPER (Common Platform Error Record) logs.

Designed and optimized the memory logging mechanism in BMC firmware to ensure efficient storage and retrieval of diagnostic data, improving system performance and reliability under constrained memory and resource environments.

Conducted in-depth fault analysis and field studies across multiple memory technologies including HBM, DDR4, and DDR5, contributing to system-level RAS improvements in hyperscale data center environments.

Developed new adaptive scrubbing operation method for DRAM using the concepts of data poisoning and hardware/firmware level principles.

Developed a DRAM Fault Emulator to model and simulate various memory failure scenarios, significantly improving validation coverage.

Worked as Graduate Researcher in Mobile Ubiquitous Systems Information Center, CS Department, SJSU.

Developed and optimized ML-enhanced routing algorithms including LCRA, integrating predictive models with traditional network protocols to improve efficiency in latency of satellite communication networks.

Utilized GNS3 for network simulation and Python ML libraries including scikit-learn, TensorFlow, and Pandas for implementing and evaluating regression-based path prediction models such as LSTM.

Analyzed large-scale NOAA geospatial datasets to extract patterns and insights of satellite movements, informing the design of more robust and adaptive routing strategies based on LCRA for dynamic space environments.

Worked as a full-time intern in the NCNG Network Switch Customer Engineering group.

Maintained and optimized features and performances for comprehensive test tools to measure and benchmark critical performance metrics for Tofino network switches including packet loss, throughput, and latency using React.js, Python, C++, P4, and shell scripting.

Enhanced overall switch testing accuracy with data manipulation and process optimization on switch output.

Collaborated with the team to address customer-reported issues and bugs, contributing to troubleshooting and resolution processes for network switch software and firmware.

Developed automatic Ticket Email Reminder application mainly using Selenium web driver and Python Flask.

Implemented SDE version updater system using Python and shell script.

Fall 2022 (Sep - Dec), Spring 2023 (Jan - May)

Worked as a teaching assistant for Computer Game Design and Programming (CS134) course, composed of 30-40 students.

Helped students with programming labs, assignments, and projects.

Graded assignments, quizzes, labs, and exams.

Used C++ with OpenFrameworks library for implementation.

Provided active code reviews on students’ game and graphic algorithm implementations.

Held office hours to assist students in understanding algorithms and implementation details.

Implemented frontend using Vue.js framework and graphs, charts, and plots using Python data engineering, and visualization libraries. Connected backend using Golang to access the PostgreSQL database.

Designed the dashboard page for specialists to view and analyze neural data collected from children.

Gained valuable experience in designing user-centric interfaces for specialized scientific applications, balancing complex data presentation with ease of use.