I build testing and debugging tools that make machine-learning failures —
numerical instability, hallucination, silent regressions — easier to detect,
reproduce, and fix.
Anwar Hossain Zahid
sig 0.420 · drift +0.00
## News · recent log
News
Launched Today's AI, a platform for discovering AI tools and learning to use them, built with Prof. Wei Le for K-12, university, and self-directed learners. link →
Paper on Soft Assertions for detecting numerical instability in ML applications accepted at FSE 2025. link →
Preprint on hate speech detection with LLMs and geographical context posted to arXiv. link →
Preprint on testing GPU numerics across NVIDIA and AMD posted to arXiv. link →
Received Honorable Mention at the LLNL Summer SLAM & Poster Symposium 2024.
Started a summer internship with the Parallel Systems Group at Lawrence Livermore National Laboratory. link →
## About
From shipping software to studying why it fails.
I am a Ph.D. student in Computer Science at Iowa State University, advised by
Prof. Wei Le in the Program Analysis and AI Lab. My
research focuses on reliable AI systems, numerical debugging, and software engineering techniques
for machine learning systems.
Before starting my Ph.D., I spent four years as a software engineer on banking, e-governance, AI,
and mobile platforms. That industry background shapes how I approach research: I care about methods
that can become practical tools for developers and researchers. A fuller timeline is on the
extended about page.
## Research interests
Research Interests
LLM hallucination
AI reliability
Software engineering for AI systems
Interpretable / white-box analysis
Human-centered AI tools
## Publications
Peer-reviewed & preprint work
On ML reliability, LLM evaluation, and numerical correctness.
FSE 2025 / PACMSE
Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions
Shaila Sharmin, Anwar Hossain Zahid, and collaborators
Introduces Soft Assertions, a method for detecting and triggering hidden numerical instability bugs in machine learning applications.
% TODO: verify full author list — "et al." is a placeholder.
@article{sharmin2025softassertions,
title = {Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions},
author = {Sharmin, Shaila and Zahid, Anwar Hossain and others},
journal = {Proceedings of the ACM on Software Engineering (PACMSE), issue FSE 2025},
year = {2025},
url = {https://arxiv.org/pdf/2504.15507}
}
arXiv:2502.19612
Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization
Anwar Hossain Zahid, Monoshi Kumar Roy, and collaborators
Evaluates how large language models perform on hate speech detection when geographic and social context are included.
% TODO: verify full author list — "et al." is a placeholder.
@misc{zahid2025hatespeech,
title = {Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization},
author = {Zahid, Anwar Hossain and Roy, Monoshi Kumar and others},
year = {2025},
eprint = {2502.19612},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2502.19612}
}
arXiv:2410.09172
Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs
Anwar Hossain Zahid, Ignacio Laguna, Wei Le
Studies numerical differences between NVIDIA and AMD GPU executions and their implications for reproducibility and portability.
% TODO: verify full author list — "et al." is a placeholder.
@inproceedings{mia2020virtualinternship,
title = {A Conceptual Design of Virtual Internship System},
author = {Mia, Raihan and Zahid, Anwar Hossain and others},
booktitle = {2020 23rd International Conference on Computer and Information Technology (ICCIT)},
year = {2020},
publisher = {IEEE},
url = {https://ieeexplore.ieee.org/document/9392713}
}
## Experience
Four years in industry, then a national lab.
Software engineering across banking, e-governance, and mobile, plus a research internship at Lawrence Livermore.
Built tooling for cross-platform floating-point precision analysis across heterogeneous GPU architectures, including HIP backend code generation for the Varity project; earned an Honorable Mention at the LLNL Summer SLAM & Poster Symposium.
Nov 2020 – May 2022
Software Engineer · Reve Systems
Worked on ERP, procurement, accounting, and compliance systems for government operations.
Nov 2019 – Nov 2020
Software Engineer · ERA-InfoTech Ltd.
Built a FinTech chatbot, face recognition, remittance integration, and RPA systems for banking workflows.
Developed Android ROM and feature-phone OS enhancements for consumer devices.
## Projects
Selected systems & applied work
Coursework and smaller repositories are collapsed below.
Today's AI — Find AI tools and learn how to use them
A web platform that helps K-12, undergraduate, and graduate learners — and anyone curious about AI — discover the right AI tools and learn to use them, built as Creator & Lead Developer under the direction of Prof. Wei Le.
GPU Numerical Testing – HIP Code Generation in Varity
Contributed to the LLNL Varity project by implementing HIP backend generation for GPU kernel testing, enabling cross-platform numerical consistency evaluation.
Extended a class project to evaluate hate speech detection models using geographical metadata. Later adapted for large language model testing and published in 2025.
MoneyGram SOAP API Integration
— TODO: verify scope/details — inferred only from the repo name. Integrated a SOAP-based API with MoneyGram remittance services as part of banking platform work.
COM S 572 – Machine Learning Project
— Implemented and evaluated ML algorithms for natural language processing tasks. Later extended for LLM experiments and paper publication.
Othello AI Agent
— Developed an intelligent Othello game-playing agent using adversarial search algorithms and heuristic evaluation functions.
Mancala Game Simulation
— Created a Mancala game engine with an AI opponent using minimax and heuristic strategies.
Ray Tracing Renderer
— Built a ray tracing engine from scratch to render 3D scenes with reflection, refraction, and shading.
Teaching assistant in the
Department of Computer Science
at Iowa State University, across the introductory programming and artificial-intelligence courses.
Taught the lab and recitation sections for COM S 127 (introductory
programming) — running weekly labs, developing course and assessment materials, designing
grading rubrics, and grading assignments and exams.
Delivered lectures for COM S 472/572 (Principles of Artificial
Intelligence), covering for Prof. Jin Tian before he left the department and for
Prof. Yan-Bin Jia.
I want this blog to be a working notebook for the problems I keep returning to:
machine learning reliability, numerical instability, debugging, and the engineering dec...
Machine learning (ML) models run on massive datasets and often perform billions of floating-point calculations.
But here’s the problem: small numerical errors can snow...
When you run the same GPU program on an NVIDIA GPU and an AMD GPU, you might expect identical results.
Surprisingly, that’s not always the case — even small floating-p...
