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🌴, doing music🎸, 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.
- Integrated Claude Code, the OpenAI SDK, OpenSearch, and 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.
- Built 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
ClaudeCode
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
SpringBoot
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
Google Analytics 4💡Research Experience
LLM-based C/C++ Vulnerability Detection Benchmark
In this project, I constructed a benchmark dataset of C/C++ vulnerabilities called SecVulEval. It solves the lack of statement-level granularity and contextual information in previous datasets.
- Collected 5,867 real-world C/C++ vulnerabilities.
- Curated 25,440 functions, including vulnerable statements and contextual information, related to the vulnerabilities.
- Designed and implemented an agentic vulnerability detection framework to evaluate various LLMs on C/C++ vulnerability detection.
- Made the dataset publicly available at HuggingFace - SecVulEval for community use.
- Published in AIware 2026 - Benchmark & Dataset track entitled SecVulEval: Context-Aware Benchmarking of LLMs for Vulnerability Detection. [🏆 Awarded Best Paper in Benchmark & Dataset Track]
Python
TransformersOpenAI SDKBug Detection Framework for Java Static Analysis Tools with LLMs
Static analysis tools are widely adopted in the industry to detect bugs in software systems. However, it is important that the tools themselves are reliable, i.e., do not miss bugs or produce false positives. In this project, I created an LLM-based metamorphic testing framework to detect inconsistencies in Java static analysis tools.
- Analyzed 3 popular Java static analysis tools: SpotBugs, ErrorProne, and PMD.
- Designed and implemented an LLM-based metamorphic testing framework to uncover faulty rule implementations in Java static analysis tools.
- Evaluated 5 widely used coding LLMs—GPT-4o, CodeLlama-34B, Codestral-22B, DeepSeek-Coder-33B, and Qwen2.5-Coder-32B.—on their ability to uncover bugs in the static analysis tools.
- Uncovered total 42 faulty rule implementations in all 3 tools. All the bugs have been reported to the respective developers.
PythonJavaTransformersOpenAI SDK
SpotBugs
ErrorProne
PMDSkills & Technologies
AI
OpenAI SDKClaudeCodeTransformers
LangGraphRAG
Languages
JavaPython
JavaScript
Frameworks
SpringBoot
Node.js
PyTorch
Database & ORMs
PostgreSQLRedisHibernate
SqlAlchemyOpenSearch
DevOps
DockerGitHub ActionsJenkins
Tools
BashGitOpenTelemetryGoogle AnalyticsProjects
Education
York UniversityToronto, Canada
Shahjalal University of Science & TechnologySylhet, Bangladesh
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.