đź‘‹ Hello, I'm
Sourena Khanzadeh
I build scalable AI systems that turn cutting-edge research into production-ready models. Passionate about bridging the gap between theoretical breakthroughs and real-world applications.
I build scalable AI systems that turn cutting-edge research into production-ready models. Passionate about bridging the gap between theoretical breakthroughs and real-world applications.
I'm a passionate AI researcher and full-stack developer with over 8 years of experience with over 8 years of experience building intelligent systems that solve real-world problems. My journey began with a fascination for how machines can learn and think like humans.
I specialize in developing scalable AI architectures, from research prototypes to production-ready models. My work spans natural language processing, computer vision, and reinforcement learning, always with a focus on practical applications.
When I'm not coding or researching, you'll find me exploring new technologies, contributing to open-source projects, or sharing knowledge with the developer community.
Cutting-edge AI algorithms and methodologies
Scalable full-stack applications and systems
Bridging research and real-world applications
Ready to collaborate on something amazing?
Let's ConnectMy professional journey in AI research and software development
Conducting doctoral research in artificial intelligence, software engineering, and blockchain-based systems while supporting undergraduate teaching, academic mentorship, and research development at Toronto Metropolitan University and the Toronto Institute for Computer Science Research.
Performed applied AI research focused on knowledge infusion, retrieval-augmented generation, and large language model enhancement, contributing to prototype development, literature analysis, and technical experimentation within a national research environment.
Developed full-stack software solutions for an industry-partnered Mitacs project with NTN Bearing Corporation, focusing on scalable application development, cloud-backed services, and user-facing business workflows.
Interested in working together?
Download ResumeExploring the frontiers of blockchain technology, artificial intelligence, and distributed systems
My research centers on developing innovative solutions at the intersection of blockchain technology, artificial intelligence, and distributed systems. I focus on creating scalable architectures that address real-world challenges in decentralized applications and intelligent systems.
Researching scalable blockchain architectures, smart contract optimization, and decentralized applications
Developing novel AI algorithms, ensemble methods, and intelligent systems for complex problem solving
Creating distributed agent architectures for collaborative problem-solving and resource optimization
Building intelligent tools for code analysis, performance optimization, and development efficiency
S Khanzadeh, N Samreen, MH Alalfi
Smart contracts on Ethereum consume gas proportional to computation. This work presents around 28 gas-efficient Solidity patterns with examples and measured savings, categorizes them, and compares tooling for gas optimization—supporting developers who must balance cost and security.
DOI: 10.1109/QRS-C60940.2023.00056
S Khanzadeh
AgentMesh is a Python framework in which cooperating LLM agents (Planner, Coder, Debugger, Reviewer) automate software development from requirements through implementation, testing, and review—with prompt strategies, orchestration, and a case study on non-trivial tasks.
DOI: 10.48550/arXiv.2507.19902
S Khanzadeh, ECP Neto, S Iqbal, M Alalfi, S Buffett
Studies how cybersecurity domain knowledge can be infused into deep learning and reinforcement learning for automated threat defense—definitions, benefits, challenges, a roadmap for red/blue teaming, explainability, and open problems for next-generation security systems.
DOI: 10.1007/s10207-025-00987-4
D Platnick, S Khanzadeh, A Sadeghian, RA Valenzano
GANsemble connects data augmentation with conditional GANs for class-conditioned synthetic data on small, imbalanced microplastics datasets—introducing MPcGAN, SYMP baselines (FID/IS), SYMP-Filter, and oversampling guidance for class imbalance.
S Khanzadeh, MH Alalfi
SolOSphere unifies tooling for analyzing, deploying, verifying, and optimizing gas for Solidity contracts (SolO, SMARTS, SolOLab)—including GitHub ingestion and SMARTS-GPT integration—toward a full smart-contract development lifecycle.
DOI: 10.1109/SANER-C62648.2024.00010
S Khanzadeh, ECP Neto, S Iqbal, M Alalfi, S Buffett
Publisher correction to the exploratory study on infusing cybersecurity domain knowledge into deep learning for automated threat defense (International Journal of Information Security).
DOI: 10.1007/s10207-025-00987-4
S Khanzadeh, SAN Chan, R Valenzano, M Alalfi
Evaluates best-first search for code refactoring toward high cohesion and low coupling using heuristic search on an approximate refactoring state space, with examples on random problems and a Java implementation tool.
DOI: 10.48550/arXiv.2305.07594
D Platnick, D Tomasz, E Earl, S Khanzadeh, R Valenzano
Compares breadth-first search vs. restarting random walks for escaping uninformed heuristic regions in greedy search; derives expected runtimes, conditions when RRW beats BrFS, EHC-RRW variants with theory and PDDL benchmark experiments.
DOI: 10.1609/aaai.v40i43.41044
S Iqbal, S Khanzadeh, ECP Neto, S Buffett, M Sultana, A Taylor
Explores auxiliary knowledge for feature engineering so ML models better separate legitimate vs. malicious traffic—framing Knowledge-Infused Learning for cyberattack detection and evaluating benefits for operational deployment (interpretability and false positives).
DOI: 10.1109/ISNCC61477.2025.11250444
Interested in collaborating on research projects?
Get In TouchReady to collaborate on something amazing? Let's connect and discuss how we can work together.
Primary contact method
Professional network
Code repositories
Whether you're interested in AI research, blockchain development, or software engineering projects, I'm always excited to explore new opportunities and collaborations. Feel free to reach out!
Quick copy my email:
sourena.khanzadeh@gmail.com