ECCV 2026 · published research
Tessellating the Earth
A location encoder with learnable spherical partitions. Co-authored research with public code and pretrained weights.
Research Associate · WashU
Hamza Iqbal
machine learning, computer vision, and research engineering
I build vision models, retrieval systems, and the tools to understand how they behave. I’m a Research Associate in Dr. Nathan Jacobs’ lab at WashU and Chief Scientist at 1088 Advisors, where I build research analytics for universities.
My background spans automotive radar, healthcare data engineering, and neuroscience. Across those settings, I like turning a research question into software people can use.
M.S. CS · WashU 2026
B.S. Math · Mizzou 2020
01Now
September 2026- Extending a retrieval method for planet-scale image geolocalization that searches a hierarchical gallery instead of encoding every tile. The paper is under review.
- Building the analytics stack at 1088 Advisors: research-portfolio benchmarking and topic clustering for universities, on top of NSF, OpenAlex, USPTO and NIH data.
- Exploring machine learning and research engineering roles, especially in Boston.
02Recent
- Tessellating the Earth is published at ECCV 2026. The talk and poster are online.
- Finished my M.S. in Computer Science at WashU in May 2026.
- Taught as the TA for CSE 4470, Automata & Theory of Computation, in Spring 2026.
03Selected work
all projects
Radar engineering · Uhnder
PySCOTT
A Python/Dash modeling tool whose predictions informed production test limits and customer coverage maps.
LLM evaluation · public code
When retrieval helps
A multi-model QA harness that separates retrieval quality from answer accuracy and tracks the cost of each question.
Full-stack product · private app
Intendo
A deliberate daily planner with transactional history, revision-checked saves and an agent CLI that previews and verifies changes.