Tanzim Hossain Romel

M.Sc. student @ University of Alberta · AI4SE · trustworthy AI agents

> SREGym blog on turning postmortems into SRE benchmark problems

> GTA/GRA at UAlberta, TA for CMPUT 174

type 'help' for commands, or just scroll

$ whois tanzim

Tanzim Hossain Romel — Lake Minnewanka, Banff National Park, September 2026.

name: Tanzim Hossain Romel
role: M.Sc. student, Computing Science
org: University of Alberta
advisor: Dr. Zhou Yang
group: U-A-Goose Lab
focus: AI4SE, LLM4Coding, trustworthy AI, AI for SRE, long-horizon coding agents
location: Edmonton, Alberta
email: tanzimho@ualberta.ca
tanhromel@gmail.com

$ cat about.txt

I study how AI agents behave in real software systems, and how to make their decisions inspectable, reliable, and trustworthy.

I bring about three years of professional software-engineering experience, formerly at IQVIA.

My research interests are AI4SE, LLM4Coding, trustworthy AI, long-horizon coding agents, and AI for SRE.

I care about focused, sustained work. Here is how I think about work ethic.

I live in Edmonton, Alberta. Fun fact: Edmonton’s North Saskatchewan River Valley is one of the largest stretches of connected urban parkland in North America.

$ cat links.txt

email scholar github linkedin orcid x cv

$ tail -n 10 news.log

2026-09 PRESS
SREGym blog: how we turned real-world postmortems into reproducible SRE benchmark problems. Blog · Tianyin’s post
2026-09 NEW
I have started graduate study in Computing Science at the University of Alberta, in the U-A-Goose group. Link
2026-06 SUBMIT
Submitted ‘The Choice Can Be the Attack: Auditing Aligned Backdoors in LLM Agents’ to the Transactions of the Association for Computational Linguistics (TACL) 2026 with Chowdhury Rakin Haider. Link
2026-06 NEW
Started a remote summer research internship at the University of Illinois Urbana-Champaign through UIUC++ Summer Research in Software Engineering (SRSE) 2026 with Professor Tianyin Xu. Link
2026-02 SUBMIT
Resubmitted ‘An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems’ to ACM Transactions on Software Engineering and Methodology (TOSEM) 2026. Preprint available on arXiv. Link
2025-10 SUBMIT
Submitted ‘An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems’ to the Mining Software Repositories (MSR) 2026 conference. First large-scale cross-platform security study analyzing ~45,000 repositories across 5 major ML platforms. Link
2025-05 PRESS
Honored with the IQVIA Impact Program Silver Award for outstanding performance and contributions to the KPI Library team. Link
2024-10 SUBMIT
Submitted ‘Sentiment Analysis of Anonymous Crisis Reports in Bangladesh’ to ACM CSCW 2025, analyzing crowd-sourced reports from Bangladesh’s 2024 national crisis using transformer models. Link
2023-06 NEW
Joined IQVIA as a Software Development Engineer on KPI Library, the dynamic reporting layer within Orchestrated Analytics. Link
2023-05 NEW
Completed B.Sc in Computer Science and Engineering from Bangladesh University of Engineering and Technology with a GPA of 3.53/4.00. Link

[all news]

$ ls ./publications/

2026

arXiv
An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems

Mohammed Latif Siddiq, Tanzim Hossain Romel, Natalie Sekerak, and 2 more authors

2026

Preprint available on arXiv

Abs arXiv Bib PDF

Large-scale cross-platform security study of roughly 45,000 repositories across five ML model hosting ecosystems, measuring unsafe deserialization, eval injection, malware signals, and recurring developer security misconceptions.
@misc{siddiq2027rce, title = {An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems}, author = {Siddiq, Mohammed Latif and Romel, Tanzim Hossain and Sekerak, Natalie and Casey, Beatrice and Santos, Joanna C. S.}, year = {2026}, note = {Preprint available on arXiv}, }
TACL
The Choice Can Be the Attack: Auditing Aligned Backdoors in LLM Agents

Tanzim Hossain Romel and Chowdhury Rakin Haider

2026

Submitted to TACL 2026; manuscript not public

Abs Bib

LLM agents can be backdoored without visibly failing the task: a trigger can steer an agent toward an attacker’s preferred valid option while the final answer still looks acceptable. SHIFT (Structured Hidden Influence Test) reruns matched tasks with and without a known trigger and checks whether the changed choice favors the attacker’s target after accounting for ordinary option quality such as price or rating.
@misc{romel2026shift, title = {The Choice Can Be the Attack: Auditing Aligned Backdoors in {LLM} Agents}, author = {Romel, Tanzim Hossain and Haider, Chowdhury Rakin}, year = {2026}, note = {Submitted to TACL 2026; manuscript not public}, }

2025

CSCW
Sentiment Analysis of Anonymous Crisis Reports in Bangladesh

Tanzim Hossain Romel

2025

Submitted to the ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW)

Abs Bib PDF

Transformer-based analysis of 124 anonymous crisis reports from Bangladesh’s 2024 national crisis, using a multilingual pipeline for Bengali and Romanized Bengali to study crowd-sourced sentiment in a high-risk setting.
@misc{romel2025ureporter, title = {Sentiment Analysis of Anonymous Crisis Reports in Bangladesh}, author = {Romel, Tanzim Hossain}, year = {2025}, note = {Submitted to the ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW)}, }

[all publications]

$ ls ./projects/

ctxhelm: agent-native context compilerLocal-first context plans, release proof, and source-free agent evaluation
ContextLedger: context accounting for coding agentsA research notebook on OpenCode compaction, provenance, and live GPT-5.5 experiments
PatchSmith: a harness for repair agentsSystem design and R&D notes for bounded patches, sandbox validation, and auditable repair runs
1BRC C# on Apple SiliconA .NET 10 NativeAOT performance case study: byte parsing, native aggregation, ARM64 tuning, and a size-aware macOS pread path
Blockchain Based Ticketing PlatformA practical approach to reducing ticket fraud and abusive resale
EventFly – Distributed Microservices Event PlatformA six-person BUET course project for event creation, ticketing, announcements, participant engagement, analytics, and payments, implemented with Node.js, React, NATS, Kubernetes, MongoDB, Redis, and Stripe.

[all projects]

$ cat research.txt

I work on three connected questions.

Long-horizon coding agents. How can they preserve context, repository memory, and architectural intent as software evolves? See ContextLedger.
AI for SRE. How should agents be evaluated when diagnosis and recovery happen inside live reliability conditions? See SREGym.
Trustworthy AI. How can we inspect agent choices, security boundaries, and evidence when the final answer still looks acceptable? See SHIFT.

$ history | grep job

Graduate Teaching Assistant (GTA) · University of Alberta

2026-09 – present

Since September 1, 2026. Department of Computing Science.

> Teaching assistant for CMPUT 174

> Support University of Alberta teaching through a GTA appointment
Graduate Research Assistant (GRA · GRAF) · University of Alberta

2026-09 – present

Since September 1, 2026. M.Sc. student in Computing Science supporting graduate research in software engineering and dependable AI.

> Graduate research with the U-A-Goose software engineering group under Dr. Zhou Yang

> Support University of Alberta research through a GRA appointment with GRAF funding
Remote Research Intern · UIUC

2026-06 – 2026-08

June–August 2026. Remote summer research internship at the University of Illinois Urbana-Champaign through UIUC++ Summer Research in Software Engineering (SRSE) 2026 with Professor Tianyin Xu’s group,...

> Curated real-world postmortem reports into reproducible SRE benchmark problems on SREGym, weighing realism, reproducibility, cost, and utility

> Worked on software engineering research with an emphasis on reliable systems and rigorous empirical evaluation
Software Development Engineer 1 · IQVIA

2023-06 – 2026-06

June 2023–June 2026. Backend engineer on IQVIA’s KPI Library, the dynamic reporting layer within Orchestrated Analytics, working across configuration, dashboard, analysis, and export workflows for healthcare...

> Built and maintained C#/.NET services and shared components across four KPI Library workflow areas—configuration, dashboard, export, and gateway; used EF Core with...

> Refactored repeated filter-resolution logic into reusable query components, consolidating 6 duplicated implementations into 2 shared components; centralized validation and business rules and...
Full Stack Engineer · Mindshare Bangladesh (Part-time)

2021-04 – 2021-11

April–November 2021. Built an e-commerce aggregator platform that let brands promote products by pulling listings from multiple e-commerce sites across Bangladesh.

> Built a web scraping system with Scrapy that collected product data from about 20 major e-commerce platforms in Bangladesh

> Deployed and maintained the scraper as a ScrapyRT server on DigitalOcean, enabling real-time extraction via API endpoints

[full cv]

$ cat education.txt

University of Alberta, M.Sc in Computing Science
September 2026 - Present
Bangladesh University of Engineering and Technology, B.Sc in Computer Science and Engineering
April 2018 - May 2023

$ ls ./posts/

2026-09-29 Working Hard Means Working Deep and Resting on Purpose
2026-06-18 Building a fast 1BRC solver in C# on Apple Silicon
2025-06-01 Memory Management in Production: Avoiding the Silent Killers

[all posts]