Skip to content
View safishamsi's full-sized avatar

Block or report safishamsi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
safishamsi/README.md

Safi Shamsi

AI Researcher working across knowledge graphs, retrieval systems, disinformation ML, and LLM inferencing, with a focus on healthcare and defence applications. I hold a Master's in Data Science with Distinction from the University of Birmingham and currently build AI systems at Valent in London. Outside research, I play chess and have a serious interest in fashion design, two disciplines that, like AI, reward both intuition and rigorous thinking.

Research

MICAD 2025 · Oral Presentation · Springer LNEE

Experience

  • AI Engineer, Valent (Jan 2026 - Present)
  • Graduate Researcher, Institute for Data and AI, University of Birmingham (Jul 2025 - Sep 2025)
  • AI Engineer, SWAWE (Feb 2024 - Jan 2026)

Education

MSc Data Science (Distinction) · University of Birmingham · 2025
Thesis: Knowledge-Graph-Based Hybrid RAG System for Academic Search

Technical Focus

Knowledge Graphs · Retrieval-Augmented Generation · Explainable AI · Medical AI
Multi-modal Deep Learning · Defence Tech · Online Manipulation & Disinformation

Links

LinkedIn Google Scholar Gmail

Pinned Loading

  1. graphify graphify Public

    AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw, Factory Droid, Trae). Turn any folder of code, docs, papers, or images into a queryable knowledge graph

    Python 16.3k 1.7k

  2. mycetoma-kg-rag mycetoma-kg-rag Public

    Multi Modal Knowledge Graph Augmented Retrieval for Explainable Mycetoma Diagnosis - MICAD 2025

    Python 20 3