Loading Portfolio...
Machine Learning Engineer based in Nairobi, Kenya. I take AI/ML research papers and turn them into working systems built for African markets. My current focus is multi-agent LLM systems — I built TradingAgents, a 13-agent framework that debates and trades NSE equities, adapting a UCLA/MIT paper for frontier market constraints like T+3 settlement, KES-denominated portfolios, and illiquid order books.
I also build production AI tools for professionals — an LLM-powered financial statement auditor using RAG and a capital gains tax engine that automates KRA compliance for Kenyan accountants. MSc Computer Science candidate with 3 IEEE publications spanning medical imaging, NLP, and financial assessment. I work across the full stack: Python, LangGraph, FastAPI on the backend; React and Next.js on the frontend.
An AI system that does what lawyers and accountants do for Capital Gains Tax. Feed it any property timeline and it applies ATO rules, performs full CGT analysis, and generates detailed reports work that traditionally takes professionals hours, done in seconds.
View ProjectAn AI-powered business consultant that helps Kenyan entrepreneurs with budgeting, licensing requirements, business ideas, and location selection, everything a qualified business advisor can do.
View ProjectImplementing global AI/ML research papers to solve local problems.
Multi-agent LLM trading system for the NSE, implementing the TradingAgents paper (UCLA/MIT). Four parallel AI analysts debate and synthesize market data, fundamentals, news, and sentiment to produce trading decisions — adapted for NSE constraints like T+3 settlement, KES commissions, and frontier market illiquidity.
Live Demo Coming SoonBased on arXiv:2412.20138
An LLM-powered auditing system that ingests Kenyan company financial statements (PDFs), chunks and embeds them with RAG, and produces structured audit reports — flagging IFRS violations, material misstatements, and going-concern risks. Built to handle the nuances of Kenyan regulatory filings (CMA, NSE listing rules, Companies Act 2015).
Read the PostSelected research contributions in data science and technology for development.
Kinyanjui, Samson, Juliet Moso and Patrick Gikunda.
2025 IST-Africa Conference (IST-Africa), 2025.
Kinyanjui, Samson and Benson Kituku.
IEEE International Conference on ICT4DA, Bahir Dar, Ethiopia, 2025.
Kinyanjui, Samson, Felix Lopuran, Peter Kimanga, Edna Mugoh, Dennis Kiprotich, and Patrick Gikunda.
IEEE International Conference on ICT4DA, 2024.
AI/ML paper breakdowns, implementations, and research notes.
A deep dive into the Transformer architecture that revolutionized NLP and became the foundation for modern LLMs.
Read moreFrom research paper to production app — building an LLM-powered auditor for Kenyan company financial statements with RAG, FastAPI, and Next.js.
Read moreFrom UCLA/MIT research paper to a working multi-agent LLM system that debates, analyzes, and trades NSE equities — adapted for frontier market constraints.
Read moreLet’s connect and build something great. I’d love to hear from you!