Sreeja Apparaju

Hi, I’m Sreeja.

I’m a machine learning engineer at Snap, working on ads auction and core pacing controller.

I graduated from UC Berkeley with degrees in Computer Science and Economics, where I worked on computational economics research (Sustainable Shared-Prosperity Policy Index & Open Policy Analysis), taught Data 88E as a head student instructor, and ran Berkeley Venture Capital.

I am interested in board games, badminton, reading, and trying new restaurants. You can reach me at sapparaju23@gmail.com.

Publications

2 papers
  • 2026

    Compute Allocation for Reasoning-Intensive Retrieval Agents

    Sreeja Apparaju, Nilesh Gupta

    ICLR 2026 — Workshop on Memory for LLM-Based Agentic Systems

  • 2026

    Feedback Control for Small Budget Campaigns in Advertising

    Sreeja Apparaju, Yichuan Niu, Xixi Qi

    The Web Conference 2026 — Workshop on Emerging Trends in Web Advertising