Ramya Olichandran

About Ramya Olichandran

I’m an Ads Platform & Infrastructure Engineer with experience in building large-scale, revenue-critical systems that sit at the intersection of machine learning, streaming data, search, and distributed infrastructure.I drove cross functional initiatives across Search indexing, ranking, search mid-tier, search backend, Ads Infra, Legal, Data Privacy, and Regulatory Compliance to ship systems that scale safely and globally. One such effort powered LinkedIn Ads External Developer APIs, indexing 1.2B member profiles, 600M feed posts, 1.4B comments, and 8B reactions, influencing ~70% of Ads revenue.On the Ads Platform side, I’ve led 0→1 initiatives that power ads targeting, and external developer API ecosystems at massive scale. I designed and built RAG + vector search–based NLP pipelines to generate precise ads targeting criteria across multiple dimensions, enabling intent-driven and semantic targeting. I also proposed and built LinkedIn Ads’ Change Data Capture (CDC) streaming platform, driving adoption across ~30 Ads use cases resulting in foundational infrastructure for Ads streaming workflows.I’ve led legacy stack transformations to modern online and streaming architectures using Flink, Samza, Kafka, and MySQL, delivering millions in cap-ex and op-ex savings while improving reliability and latency. Earlier, as a Traffic Infrastructure Engineer, I worked on the performance and reliability of Apache traffic servers serving hundreds of millions of users. I built mobile device personalization pipelines collecting device signals from 310M MAU, trained ML models for device classification (76% accuracy), and improved delivery performance across geographies for LinkedIn Stories product launch. I proposed and implemented TCP/IP optimizations and HTTP/3 (QUIC) in Apache Traffic Server, significantly improving perceived page load times for mobile apps in emerging markets. I also led performance analysis and improvements during Azure cloud migration, scaling traffic servers with lower latency and higher reliability.Across roles, I enjoy working on problems where scale, ML, streaming data, and product impact meet—turning complex infrastructure into platforms that teams rely on and businesses grow on.Interests: Ads & monetization platforms, ML-driven personalization, streaming systems, search & retrieval, large-scale infra, and agent-ready data platforms.

Experience

1. Stanford Ml

   Stanford Continuing Studies

   Feb 2026 — Present

Education

• University of Wisconsin-Madison

  Master of Science (M.S.), Computer Science

  2008 — 2010

• College of Engineering, Guindy , Anna University

  B.Tech, Information Technology

  2002 — 2006

Skills

• Objective-C
• Embedded Systems
• Pl/Sql
• Git
• Operating Systems
• C#
• Multithreading
• Eclipse
• Shell Scripting
• Tcp/Ip
• Xml
• Web Services
• Sql
• Linux
• Debugging
• Data Structures
• Algorithms
• Mobile Applications
• Software Design
• Hadoop
• Scalability
• Software Engineering
• Jsp
• C++
• Android
• Computer Science
• Object Oriented Design
• Spring
• Big Data
• Gnu Debugger
• Javascript
• Uml
• Java Enterprise Edition
• Java
• Testing
• C
• Software Development
• Python
• Computer Architecture
• Subversion