About Me
I'm a software engineer and MSc Computer Science graduate from York University. My work combines Java/Spring Boot backend development with research on LLM agents, software security, and automated testing.
At DSi and on an external assignment with Synopsys, I worked on examination-management systems, payment integrations, and CI/CD tooling. During a university research collaboration with Huawei Canada, I developed components for repository-wide test generation and agent tracing and evaluation. My research includes SecVulEval, which received the Best Dataset & Benchmark Paper award at AIware 2026, and StaAgent, accepted in ACM TOSEM.
When I'm not working, you can find me traveling🌴, playing instruments🎸, or experimenting with new technologies🧑💻.
Experience
💼Professional Experience
Research & Development Intern - University Collaboration
Developed Python components for a repository-wide agentic test generation framework that transforms software requirements and repository code into executable test scripts.
- Built agent workflows with Claude Code, OpenAI SDK, and OpenSearch/RAG; evaluated code retrieval, code maps, and token use efficiency.
- Built a forward-proxy framework to capture prompts, responses, tool calls, and session-linked agent traces.
- Designed and implemented a rule-based and LLM-based trace evaluation framework using Langfuse traces.
- Debugged, documented, and resolved failures in tool use, context awareness, instruction following, and output consistency.
- Collaborated remotely and on site with Huawei's Beijing engineering and research team.
Python
Claude Code
OpenAI SDK
OpenSearch
RAG
Opik
Langfuse
OpenTelemetryAssociate Software Engineer
Developed backend services for HEMS, a nationwide examination-management platform.
- Developed Java/Spring Boot REST APIs and PostgreSQL backend functionality for HEMS.
- Translated client requirements into backend and database designs.
- Built grading, result-processing, and reporting workflows for approximately 30,000 students annually.
- Integrated two payment gateways handling approximately BDT 4 million in annual transactions.
- Implemented mobile-client REST APIs with JWT authentication.
Java
Spring Boot
PostgreSQL
Hibernate
Redis
REST APIs
Git
LinuxSoftware Engineer (External)
Worked remotely on an external assignment through DSi with Synopsys Inc., contributing to Black Duck Detect, a software composition analysis tool that identifies dependency-related component, security, and license risks.
- Contributed Java, Groovy, and Gradle changes to Black Duck Detect.
- Migrated the Detect project CI/CD pipeline from Jenkins to GitHub Actions.
- Diagnosed and fixed two defects affecting scheduled jobs and artifact versioning.
- Migrated analytics from Google Universal Analytics to GA4, restoring a broken reporting dashboard.
Java
Groovy
Gradle
Jenkins
GitHub Actions
GA4💡Research Experience
SecVulEval - Context-Aware C/C++ Vulnerability Benchmark
Built a real-world C/C++ vulnerability benchmark with 25,440 functions covering 5,867 CVEs.
- Curated paired vulnerable/fixed code with statement-level vulnerability labels and external program context.
- Designed and implemented a multi-stage LLM-agent pipeline for context-aware vulnerability detection.
- Evaluated five LLMs at function and statement levels, with ablations and failure analysis.
- Received the Best Dataset & Benchmark Paper award at AIware 2026. 🏆
- Made the dataset publicly available at Hugging Face - SecVulEval for community use.
PythonOpenAI SDK
Transformers
Benchmark constructionLLM evaluationContext-aware agentsStaAgent - An Agentic Framework for Testing Static Analyzers
Developed an LLM-assisted, mutation-based metamorphic-testing framework for static-analysis rule implementations.
- My highlighted work uncovered 42 faulty rule implementations across SpotBugs, Error Prone, and PMD.
- Findings were reported to developers; some issues were already fixed. Status is available in the linked preprint.
- Accepted as an article in ACM Transactions on Software Engineering and Methodology (TOSEM) 2026.
PythonJavaOpenAI SDKTransformers
SpotBugsError Prone
PMDMetamorphic testingSkills & Technologies
Gen AI
PythonOpenAI SDKClaude Code
Agent SkillsRAGOpenSearch
LangGraph
Machine Learning
PyTorchOpenCLIPTransformerstorchvision
NumPy
Pandas
OpenCV
Backend
JavaPython
JavaScriptSpring Boot
Node.js
Databases & ORMs
PostgreSQLHibernateRedis
SQLAlchemy
DevOps
DockerGitHub ActionsJenkins
MavenGradleLinux
BashGit
Frontend
JavaScript
React.js
JSX
Tailwind CSS
HTML5
CSS3
Observability & Evaluation
OpikLangfuseOpenTelemetryGoogle AnalyticsProjects
LLM Agent Trace Analyzer
Designed a trace-analysis workflow for an AI test-generation agent to uncover agent failures and enable root-cause analysis.
Collected and filtered applications built on top-downloaded Hugging Face text-classification and text-generation models. Extracted code-size metrics with Lizard and analyzed implementation-size and maintainability trends using Pandas, NumPy, and Matplotlib.
Education
York UniversityToronto, Canada
Shahjalal University of Science & TechnologySylhet, Bangladesh
Publications & Recognition
SecVulEval: Context-Aware Benchmarking of LLMs for Vulnerability Detection
Md Basim Uddin Ahmed; Nima Shiri Harzevili; Jiho Shin; Hung Viet Pham; Song Wang
Proceedings of the 3rd ACM International Conference on AI-Powered Software (AIware '26) · Montreal, Canada, July 6-7, 2026 · 2026
StaAgent: An Agentic Framework for Testing Static Analyzers
Elijah Nnorom*; Md Basim Uddin Ahmed*; Jiho Shin; Hung Viet Pham; Song Wang
ACM Transactions on Software Engineering and Methodology (TOSEM) · Accepted, 2026
*Equal Contribution
A Systematic Literature Review on English and Bangla Topic Modeling
Md. Basim Uddin Ahmed; Ananta Akash Podder; Mahruba Sharmin Chowdhury; Mohammad Abdullah Al Mumin
Journal of Computer Science · 17(1), 1-18 · 2021
Get In Touch
Have a project in mind or just want to connect? Feel free to reach out to me using the form or through any of the channels below.