Istanbul, Türkiye · Open to relocation

Muhammad Mohsin
Memon

Full-stack engineer shipping production fintech systems, and an AI researcher teaching retrieval systems to know when they're unsure.

confidence score: 0.91 — high certainty, production-ready

I build software where correctness compounds — payment flows, decision engines, systems that move real money and can't afford to guess. That's what led me to my current research question: how do you make an AI system say "I'm not sure" before it costs someone money?

By day, I'm a Full-Stack Developer on a money-movement product at CentricDXB, shipping features that handle tens of thousands of API requests a month. By thesis, I'm an MSc Artificial Intelligence candidate at Beykoz Üniversitesi in Istanbul, working on confidence calibration for retrieval-augmented generation in fintech contexts.

I'm currently applying to senior frontend and full-stack roles across Europe and Türkiye, and laying groundwork for a fully-funded PhD.

Based inIstanbul, Türkiye
CurrentlyFull-Stack Developer, CentricDXB
StudyingMSc AI, Beykoz Üniversitesi
Thesis focusConfidence-calibrated RAG
Looking forSenior Frontend / Full-Stack roles
Long-termFully-funded PhD, Europe
Full-Stack Developer
CentricDXB
May 2023 — Present · Remote, UAE

Building and maintaining full-stack features across a fintech product suite — from API design to database performance to production reliability, working within a cross-functional team of 10+ engineers.

15+
Features shipped to production
50K+
Monthly API requests handled
25%
Database load reduction
95%
Code coverage maintained
40+
Production bugs resolved
MSc THESIS · IN PROGRESS
Confidence-Calibrated RAG (CC-RAG) for Real-Time Fintech Decision Support

A retrieval-augmented generation system that doesn't just answer — it quantifies how sure it is. CC-RAG scores retrieval uncertainty and maps it directly onto transaction risk levels, aiming to cut hallucination in payment and compliance decisions where a wrong answer has a real cost. Production fintech experience feeds directly into how the risk mapping is designed.

low uncertainty → auto-approve calibrating high uncertainty → escalate
Python LangChain Pinecone / Qdrant OpenAI / Llama FastAPI RAGAS React MongoDB
/ 01
FinSight

A multilingual RAG system answering financial questions across languages, built to bridge the gap between raw financial documents and plain-language answers.

RAGMultilingualLLM
/ 02
CodeReview AI

A GitHub bot that reviews pull requests automatically, flagging issues and suggesting fixes before a human reviewer even opens the diff.

GitHub APILLMAutomation
/ 03
DAS

A deep-learning NLP application that detects signals of mental health distress from text, trained and evaluated for real-world reliability.

NLPDeep Learning
82% classification accuracy

Frontend

React.js / Next.js
TypeScript
Redux
Micro-frontends

Backend & Data

Node.js
MongoDB
Python / FastAPI
LangChain / RAG systems
2024 — Present
MSc Artificial Intelligence thesis in progress
Beykoz Üniversitesi, Istanbul, Türkiye
Thesis: Confidence-Calibrated RAG for Real-Time Fintech Decision Support.
Graduated Jun 2023
BSc Computer Science
FAST — National University of Computer & Emerging Sciences (NUCES)