Sajjad Fani
Software Engineer & M.Sc. Artificial Intelligence Researcher
I am a Software Engineer and M.Sc. student in Artificial Intelligence with a background in backend engineering, distributed systems, DevOps, and applied machine learning.
My current research focuses on the reliability and robustness of AI systems in clinical decision-making, particularly tool-using large language models. Alongside my academic work, I lead backend and DevOps development for a medical toxicology team, where I build production software and AI-enabled services using Python, Django, PostgreSQL, Redis/Celery, Docker, and modern LLM APIs.
I am particularly interested in research at the intersection of Clinical AI, reliable language models, AI-enabled software systems, and production ML infrastructure.
Research Direction
My research focuses on the reliability and robustness of AI systems in clinical decision-making. My M.Sc. thesis asks whether tool-using clinical LLMs correctly change their decisions when a small but clinically decisive variable crosses a meaningful decision boundary — studied through a counterfactual benchmark in clinical toxicology. More broadly, I work at the intersection of Clinical AI, reliable and robust language models, AI-enabled software systems, and the distributed and MLOps infrastructure that production AI depends on.
What I Build
Backend Systems
High-performance REST APIs, async task pipelines, and microservices architectures using Python, Django, and Celery.
Distributed Systems
Service mesh patterns, event-driven architectures, fault-tolerant systems, and containerized deployments.
AI Integrations
Integrating LLMs and custom ML models into production backends — from OpenAI APIs to custom PyTorch deployments.
DevOps & Cloud
Containerized deployments with Docker, reverse proxying via Nginx, and CI/CD pipelines on Linux for reliable, reproducible releases.
Education
From an undergraduate foundation in Computer Engineering to graduate study — the full academic path, in reverse-chronological order.
Master of Science in Artificial Intelligence
Islamic Azad University
Thesis: Decision-Boundary Robustness in Tool-Using Clinical LLMs: A Counterfactual Benchmark in Clinical Toxicology
Bachelor of Science in Computer Engineering
Quchan University of Technology
Quick Facts
- LocationMashhad, Iran
- Current RoleBackend & DevOps Lead @ Medical Toxicology
- Academic StatusM.Sc. Artificial Intelligence Student, Islamic Azad University
- LanguagesPersian (native), English (advanced)
- Open ToEngineering roles · Research collaborations