Backend and APIs
Production services and data-heavy analytics workflows.
C#/.NET · EF Core · REST APIs · Microservices
Researcher · software engineer · open-source contributor
Tanzim Hossain Romel
I study AI agents in real software systems. I want to know what they read, which actions they take, how they recover from failures, and whether their evidence holds up.
My work spans software reliability, agent security, empirical software engineering, program analysis, and developer tools. I also have three years of software and AI engineering experience, building backend services, cloud data workflows, and LLM/RAG features for healthcare analytics.
UIUC++ SRSE 2026
Incoming Alberta M.Sc.
BUET CSE- Dhaka, Bangladesh
Current work
Remote Research Intern, UIUCJune–August 2026
Engineering profile
What I build with
Three years of production software and AI engineering, alongside hands-on systems and open-source work.
AI and agent systems
LLM/RAG workflows and research tools connected to real software systems.
Python · LangGraph · MCP · RAG · LLM evaluation
Systems and open source
Developer tools, program analysis, and multi-language open-source contributions.
Rust · Go · TypeScript · Java · C++
Cloud, data, and reliability
Deploying, tuning, and observing cloud-native services and data stores.
AWS · PostgreSQL · MongoDB · Docker · Kubernetes · OpenTelemetry
About
I learn by building
I grew up in Rajshahi and now live in Dhaka. I like work that starts with a research question and ends with something I can run, test, or measure.
That usually means reading papers, tracing failures, building tools, and writing down what actually happened.
Research agenda
Reliable agents in real software systems
My current work falls into six related areas.
-
01 · Reliability-agent evaluation
Research context · UIUC++ SRSE 2026 SREGym: AI for SRE and reliability-agent evaluation
How can we evaluate an SRE agent in a live software environment without mistaking a shallow recovery for a reliable one?
Through UIUC++ SRSE 2026, I am working on SREGym, a benchmark for evaluating SRE agents in live system environments and real-world reliability problems.
-
02 · ML ecosystem security
Study methodology · five hosting ecosystems Remote Code Execution in ML model hosting ecosystems
What risks emerge when model-hosting platforms load community code and artifacts at ecosystem scale?
A cross-platform empirical study examines custom model-loading risk across five ML hosting ecosystems, using static analysis, malware-signature scanning, and more than 600 developer discussions.
-
03 · Agent security
System context · choices inside an agent workflow The Choice Can Be the Attack: auditing aligned backdoors in LLM agents
Can a trigger steer an agent toward an attacker’s preferred valid choice while its final answer still appears acceptable?
SHIFT compares matched tasks with and without a known trigger, then asks whether a changed valid choice favors an attacker’s target after accounting for ordinary option quality.
The manuscript is not public; this is an abstract-level summary.
-
04 · Coding-agent systems
Research direction
Context, retrieval, and auditable repair
How can coding agents preserve exact session facts, inspect the right files, and leave testable repair evidence?
ContextLedger measures what survives context compaction, ctxhelm and HelmBench evaluate retrieval efficiency, and PatchSmith records bounded repair runs with sandbox validation and inspectable artifacts.
-
05 · Agent memory
Research direction
History-aware vibe coding
Can coding agents preserve architectural intent while developers work through fast natural-language programming loops?
This emerging direction studies how agents should use commit history, prior edits, repository memory, and design intent without losing the speed of vibe coding.
-
06 · Multi-agent verification
Research direction
VeriSchema: verified database-schema generation
How can specialized agents generate relational schemas while formal checks and targeted repair keep the result consistent?
VeriSchema uses agents for entity extraction, relationship mining, normalization, and repair, with Z3 checks and component-level retries for relational consistency.
Publications and artifacts
Research record
Papers, submissions, and the public artifacts behind them.
2027
An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems
Under review at International Conference on Software Engineering (ICSE)
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.
2026
Research paper
The Choice Can Be the Attack: Auditing Aligned Backdoors in LLM Agents
Submitted to Transactions of the Association for Computational Linguistics (TACL)
SHIFT tests whether a known trigger changes which valid option an agent chooses, then asks whether that movement favors an attacker's target after accounting for ordinary option quality.
Experience
Research and production engineering
A short account of the work I did and the outcomes I can support.
Remote Research Intern, UIUC
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, focused on software and systems reliability research.
June–August 2026
- Working on software engineering research with an emphasis on reliable systems and rigorous empirical evaluation
- Reading systems and software reliability literature, prototyping research ideas, and preparing artifacts for reproducible evaluation
Software Engineering Research · Systems Reliability · Empirical Evaluation · Reproducibility
Software Development Engineer 1, IQVIA
Backend engineer on the KPI Library team, building .NET/C# microservices for healthcare analytics workflows over large patient-level datasets. IQVIA (NYSE: IQV) provides analytics, technology solutions, and clinical research services to the life sciences industry, with 74,000+ employees across 100+ countries.
June 2023–June 2026
- Built and deployed cloud-native healthcare analytics services with C#/.NET Core and EF Core on AWS (Lambda, EC2, S3, DynamoDB); shipped RESTful APIs used by global pharmaceutical clients
- Refactored a complex healthcare-analytics filter path into reusable query components, reducing duplicated business rules and improving filtering performance by 70% in the targeted workflow
- Helped build a LangGraph/LangChain workflow using MCP and RAG to turn analyst prompts into structured dashboard setup, modification, analysis, and export actions
- Reduced selected complex query execution times by 60% through PostgreSQL query planning, indexing, and materialized views
70%targeted filtering improvement60%selected query-time reduction95%export workflow coverage35%deployment-time reductionC# · .NET Core · EF Core · PostgreSQL · MongoDB · AWS ·...
Full Stack Engineer, Mindshare Bangladesh (Part-time)
Built an e-commerce aggregator platform that let brands promote products by pulling listings from multiple e-commerce sites across Bangladesh.
April–November 2021
- 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
- Built the backend with Express.js and MongoDB to manage, process, and aggregate product data from the scraper
- Created APIs for brands to host ads and integrate with the aggregated data
Python · Scrapy · ScrapyRT · Express.js · Node.js · MongoDB · DigitalOcean ·...
Education
Education
My academic path, from Rajshahi to BUET and Alberta.
Starting September 2026 · Incoming
M.Sc in Computing Science
Starting the M.Sc in Computing Science program in September 2026, with interests in software engineering research, trustworthy AI, distributed systems, and LLM systems. I will be joining the U-A-Goose software engineering group at the University of Alberta, supervised by Dr. Zhou Yang, with affiliation to Amii (Alberta Machine Intelligence Institute).April 2018 - May 2023
B.Sc in Computer Science and Engineering
Bangladesh University of Engineering and Technology
Dean's List Award - Level 2 (outstanding academic performance)
Notable Courses: Machine Learning, High Performance Database Systems, Fault Tolerant Systems, Data Structure and Algorithms, Operating Systems, Computer Security
2015 - 2017
Higher Secondary Certificate (HSC)
Placed 15th in Rajshahi Board, received Talentpool Scholarship, A+ in all subjects with 96.5% marks in Physics, Chemistry, and Higher Mathematics
Engineering and open source
Research systems, developer tools, and selected builds
My current agent tools come first. The rest shows the systems and ML work that led to them.
Open source
RefactoringMiner MCP
Active RefactoringMiner development with Professor Nikolaos Tsantalis; I helped build MCP access for coding agents and contribute to the JetBrains integration collaboration.
ctxhelm and HelmBench
A released Rust context compiler and source-free evaluation harness for testing whether coding agents inspect the right files with less irrelevant reading.
ContextLedger
Typed, provenance-carrying session facts, exact token accounting, and measurable context compaction for long coding-agent runs.
PatchSmith
An auditable repair harness with bounded context, structured patch proposals, sandbox validation, trace capture, and inspectable artifact directories.
Open source
Selected open-source contributions
Curated contribution evidence across EF Core, GenHTTP, deepagents, TypeScript, LangChain, and other developer-tooling repositories.
Systems build
Systems and performance builds
1BRC C# on Apple Silicon, a Go database engine, a Go container runtime, a compiler, a ray tracer, TCP Vegas+, and the distributed EventFly platform.
Applied ML
Applied ML and learning builds
Bangla digit recognition from NumPy and OpenCV primitives, BERT-context image captioning, and a mini deep-learning framework with autodiff and tensor operations.
Recognition
Awards and milestones
A few awards and competition results.
2025
IQVIA Impact Program — Silver
Performance, critical issue resolution, and essential feature delivery.
2022
2nd place · Bangla handwritten digit recognition
Second among 120 students; a custom CNN from NumPy and OpenCV primitives reached 95.9% test accuracy.
Level 2
BUET Dean's List
Academic recognition for sophomore-year performance.
2017
National Physics Olympiad prize
National recognition in theoretical and practical physics.
2017
National Chemistry Olympiad prize
National recognition in chemistry alongside the physics award.
2017
Talentpool HSC Scholarship
Merit scholarship after placing 15th in the Rajshahi Education Board.
Recent milestones
What changed recently
Recent changes to my research and academic plans.
SHIFT submitted to TACL 2026
Aligned-backdoor auditing work submitted with Chowdhury Rakin Haider.
ML hosting RCE under review at ICSE 2027
Cross-platform empirical security study with a public arXiv artifact.
Started UIUC++ SRSE research internship
Summer research with Professor Tianyin Xu's systems reliability group.
Incoming University of Alberta M.Sc.
Joining U-A-Goose and Amii under Dr. Zhou Yang.