Senior AI/ML Engineer building production AI systems — deep learning, computer vision, LLMs, RAG pipelines, and identity verification at scale. Currently at Agregar Technologies, where I build and ship AI-powered KYC, AML, and document verification systems serving enterprise financial institutions across Africa. I work primarily with Python, PyTorch, TensorFlow, YOLO, FastAPI, and AWS. BSc Computer Science from the University of Ghana. Jim Leech Mastercard Foundation Fellow at Queen's University, Canada.
Download Resume ↓Built core AI/ML systems powering identity verification and financial compliance for enterprise clients across Africa. Developed ScoreX (AI credit scoring), fine-tuned ResNet and YOLO models for document verification and smart ID capture, built AML transaction monitoring engines, and shipped a deepfake detection system for biometric fraud prevention.
Python, PyTorch, TensorFlow, ResNet, YOLO, OpenCV, FastAPI, PostgreSQL, Redis, Docker, AWS, LangChain, Hugging FaceBuilt a real-time predictive surveillance system that interfaces with IP cameras to detect and predict suspicious activity using computer vision and ML models. Led a team of 5 engineers.
Python, PyTorch, OpenCV, TensorFlowLed a team of 4 in an AI hackathon organized by SuperFluid Labs in collaboration with AI Commons. Placed 4th out of 12 competing teams.
Python, LLMs, Prompt EngineeringLed technical development for an agriculture technology project integrating data-driven approaches to cassava processing and export optimization.
Python, Data Analysis, ML ModelingBuilt websites and web applications for clients. Streamlined codebases and improved user experience across multiple projects.
JavaScript, HTML, CSSRetrieval-Augmented Generation pipeline using LlamaIndex for advanced document Q&A with agentic reasoning.
Python, LlamaIndex, Vector DBAI-powered legal assistant that helps users navigate legal documents, get instant answers, and understand complex legal language.
Python, LLMs, RAG, Next.jsReal-time computer vision system interfacing with IP cameras to detect and predict suspicious criminal activities before they occur.
Python, PyTorch, OpenCV, YOLOSoftware that interfaces with IP cameras to detect, classify, and track various objects in real time using deep learning models.
Python, OpenCV, Deep LearningProduction biometric fraud prevention — detects AI-generated faces, video replays, and printed photo spoofing in live deployment.
Python, PyTorch, Deep Learning, OpenCVML-powered credit scoring system that assesses creditworthiness from behavioral and transactional data for faster lending decisions.
Python, Scikit-learn, FastAPI, PostgreSQL