Shoumik Chowdhury

Machine Learning Engineer at Andium, working across computer vision, ML platforms, and LLM applications. Believer in tech for social good and proud NYC-DSA member.

Research

Before moving into industry, I spent time in academic research across robotics and computational social science. These projects shaped how I think about ML — not just as models and metrics, but as tools that interact with real systems and real people.

Robotics & Computer Vision

For my undergraduate thesis under Dr. Tarem Ahmed, I built a low-cost robot capable of interior mapping using sonar-based SLAM (Simultaneous Localization and Mapping). The constraint was the fun part — making it work with cheap sonar sensors instead of expensive LiDAR. Presented at TENCON 2018 (IEEE Region 10).

Computational Social Science

At KolpoKoushol, a knowledge initiative led by Dr. Nazmus Saquib, I analyzed a decade of political discourse in Bangladeshi news media. We mapped how tight-knit groups of political leaders dominate coverage while broader national concerns get sidelined. Published at the ML4D workshop at NeurIPS 2018.


Publications

Statement Networks: A Power Structure Narrative as Depicted by Newspapers Shoumik S Chowdhury, Nazmus Saquib, Niamat Zawad, Manash Kumar Mandal, Syed Haque ML for the Developing World (ML4D) Workshop at NeurIPS 2018 Read Paper

Sonar-based SLAM Using Occupancy Grid Mapping and Dead Reckoning Muhammad S. A. Khan, Shoumik S Chowdhury, Nafis Niloy, Fatema Tuz Zohra Aurin, Tarem Ahmed IEEE Region 10 Conference (TENCON 2018) Read Paper


← Back to Home