# Yuanyuting Wang > Software Engineer at Meta | CS @ Columbia Location: San Francisco Bay Area, United States Profile: https://flows.cv/yuanyuting ## Work Experience ### Senior Software Engineer @ Meta Jan 2024 – Present | Sunnyvale, California, United States • Senior engineer on Elastic Model Serving (EMS) platform, a large-scale internal ML inference system designed to optimize for and maximally utilize opportunistic (elastic) GPU capacity; platform improvements contributed to a 2.06% increase in Meta’s global Ads Score (primary ads revenue metric) in H2 2025. • Led a P0, foundational initiative enabling the platform to serve inference requests across heterogeneous AI hardware types, future-proofing the system against hardware fragmentation. Owned extensive redesign and alignment for the next-generation EMS platform with mixed-hardware capability, and led a team of 6+ engineers on the implementation, internal A/B testing, and rollout with 0 downtime. • As the reliability point-of-contact of the team, drove cross-stack reliability roadmapping across EMS data and control planes; migrated all production models to isolated prod environment & organized half-long workstreams across team, achieving ~43% crash rate reduction, ~9–10% increase for traffic served on elastic capacity, ~10–12× faster reaction times, and ~200% fewer oncall alerts. • Drove the investigation and remediation for 30+ SEVs, delivering durable, postmortem-driven fixes for revenue-critical incidents. • Built org-wide influence via mentoring junior engineers through oncall rotations and design reviews; led technical talks on platform architecture and next-generation serving capabilities. ### Software Engineer @ Meta Jan 2023 – Jan 2024 | Menlo Park, California, United States • Project lead in implementing the Conversation Routing product, a Messenger/Instagram business-to-consumer thread-level handover protocol that allows businesses to coordinate multiple third-party service providers they are employing for different use cases. Led a team of engineers, product/content designers, product managers & partner manager to iterate on partner feedback & ship solutions to partner pain points. • Co-project lead in implementing VoIP calling third-party APIs on Messenger, which allows Messenger businesses to call customers / receive customer calls through third-party software to ensure operation scalability. Owned design of the real-time calling interface that integrated with first-party messaging infrastructure while meeting strict latency, reliability, and third-party extensibility requirements. Led a team of engineers to deliver test-ready beta 2-months early; closely coordinated with external enterprise customers to kickstart beta testing by end of 2024 ahead-of-schedule. • Designed the first end-to-end testing framework for Messenger and Instagram business messaging APIs, reducing the CI runtime by >90% and making critical tests push-blocking. ### Junior Software Engineer @ Meta Jan 2022 – Jan 2023 | Menlo Park, California, United States • Took ownership of a cross-functional messaging platform project within the first month of joining the company, delivering features across backend APIs, web, Android, and infra tooling. • Improved API reliability through expanded test coverage, high-scale load testing, and test flakiness detection. • Drove privacy, security, and compliance work, ranking among top contributors on the team. ### Software Engineer Intern @ Meta Jan 2021 – Jan 2021 | Menlo Park, California, United States - Implemented new cloud-to-access gateway (AGW) gRPC callpath in that utilizes deterministic serializations of streamed data, a.k.a. “digests”, to intelligently sync data downstream for our subscriber-management service. - Created kubernetes deployment of cloud microservice that manages batch updates of digests and cached data objects in SQL store, with added concurrency protection for when interacting with multiple client microservices. - Generalized tooling (Protobuf, SQL cachestore) used in gRPC endpoints to propagate the digests pattern across services. - Changes included in Magma v1.6 release, estimated to reduce network load from 15.7TB to 0.054TB (/month/network). ### Software Engineering Manager @ Spectator Publishing Company Jan 2019 – Jan 2021 • Developed Columbia freshman orientation website with React, HTML and CSS that accumulated over 5000 unique pageviews. • Led team and developed Columbia Housing Review web page using React/NodeJS and MySQL stack, which allows for dynamic and concurrent user content generation. • Facilitating the migration of the Columbia Spectator website, which received over 4 million page views last year, to React in collaboration with the Washington Post. • Created training program for junior engineers in web development technologies, e.g. React, Node, SQL, Git. ### Software Engineer Intern @ Lyft Jan 2020 – Jan 2020 | Menlo Park, California, United States - Worked with data infrastructure (Hive, Presto, Wavefront, Protobuf, etc.) to redesign the visibility setup for our competitive intelligence service, and achieved data transparency at every pipeline juncture. - Eliminated ~90% of the redundant network calls made to vendor through designing new endpoint logic. - Enabled structured and effective communication with downstream users by providing business-critical metrics delivered automatically to users on an adjustable cadence, among other features formulated through rounds of user interviews and iterations. ### Project Lead Developer @ Columbia Data Product Initiative Jan 2019 – Jan 2020 • Leading development of university event aggregation platform with a React/flask/Python/PostgreSQL stack, to be deployed via Heroku. • Optimizing data pipeline through caching and asynchronous handling for scalability. • Implementing ML-assisted recommendation algorithm to tailor experience towards user interest. • Deliberating marketing and engagement strategies, product scheduled for user testing during summer and official launch this fall. ### Treasurer @ Columbia Organization of Rising Entrepreneurs Jan 2019 – Jan 2020 • Managing budgeting plans for future programming, and securing corporate sponsorships for fiscal year 2019-20 through outreach programs. • Helped organize Enterprises, a weekly entrepreneurship-expository seminar open to all Columbia students. • Led CORE Giving Week, a week of panels and talks featuring NYC social entrepreneurs in celebration of community giving back. ### Researcher @ Columbia Intelligent and Connected Systems Lab Jan 2019 – Jan 2020 • Provided platform for classifying users’ apparent affective states with 79.62% prediction accuracy, utilizing Convolutional Neutral Network model for eye landmark localization, and image optic flow tracking. • Provided bio-signal preprocessing, feature engineering and implicit affective state classification service with Python-based data processing pipeline. • Co-authored paper submitted to UbiComp2019 for review. ### Researcher @ University of Florida Jan 2017 – Jan 2018 | Gainesville, Florida Area - Researched with Prof.Ge at the University of Florida on 2175 angstrom dust absorbers. - Collected data from automated observatory and conducted data analysis using quasar spectroscopy. - Used Python and IDL for data analysis and representation. ## Education ### Bachelor of Science - BS in Computer Science Columbia University Jan 2018 – Jan 2022 ### High School Diploma Shenzhen Middle School Jan 2015 – Jan 2018 ## Contact & Social - LinkedIn: https://linkedin.com/in/yuanyuting-wang --- Source: https://flows.cv/yuanyuting JSON Resume: https://flows.cv/yuanyuting/resume.json Last updated: 2026-03-22