Hello, I'm
Recent Computer Science graduate and early-career AI researcher with a peer-reviewed publication in deep reinforcement learning for autonomous quadrotor navigation. Working across autonomous systems, embedded AI, and low-resource NLP.
I recently graduated in Computer Science from the Islamic University of Madinah, where I am now pursuing an M.Sc. in Data Science. I am originally from the Central African Republic. My academic projects and peer-reviewed research have focused on deep reinforcement learning, autonomous systems, and embedded intelligence. I have also worked on NLP tools for underserved languages.
In July 2026, I founded CONACAF, a Central African company working in software, digital services, and computer-assisted language services.
Outside of academics, I have been involved in community development work in CAR, coordinating with international organizations on humanitarian initiatives.
Medina, Kingdom of Saudi Arabia
Islamic University of Madinah
Central African Republic
AI & Autonomous Systems
Developed a PPO-based autonomous navigation system for a Crazyflie-class quadrotor in Webots using a hierarchical PID+DRL architecture and a three-stage curriculum. Multi-seed experiments show that a continuous shaping gradient, exploration-noise initialization, and curriculum advancement criterion jointly determine convergence; reward polarity alone does not. The final policy achieved 95.0% success at Stage 0, 89.6% at Stage 1, and 48.4% at the hardest Stage 2 conditions.
Developed a Sango-French translation and speech prototype for Sango, the national language of the Central African Republic. Constructed a quality-filtered parallel corpus of 21,125 verse pairs, applied LoRA fine-tuning to NLLB-200, and integrated the resulting model with a speech-synthesis pipeline.
Sango-French translation prototype built from a 21,125-pair parallel corpus using parameter-efficient LoRA fine-tuning of NLLB-200. The work includes in-domain evaluation, a Meta MMS-TTS speech-synthesis component, and publicly available model resources.
Peer-reviewed study of PPO-based quadrotor navigation with obstacle avoidance in Webots. A hierarchical PID+DRL architecture, systematic reward engineering, multi-seed evaluation, and controlled ablations show how shaping gradients, exploration-noise initialization, and curriculum gating interact to determine convergence. Published in Drones on 28 August 2026.
320-hour intensive program at KAUST Academy. Built automated pipeline integrating AlphaFold2 and AutoDock Vina for computational biology. Focused on workflow optimization and reproducibility.
Configured MPI-based computing cluster for parallel computing coursework. Documented distributed systems setup and demonstrated parallel execution principles across networked nodes.
FPGA hex display system for the DE1-SoC (Cyclone V 5CSEMA5F31C6). Implements a reusable 7-segment decoder module supporting full hexadecimal (0–F) output across multiple displays using Verilog HDL.
Autonomous obstacle-avoidance robot powered by a neural network deployed entirely in FPGA hardware. The DE1-SoC (Cyclone V) runs inference in ~1 microsecond using a compact 3-8-3 network in Q6.10 fixed-point arithmetic. Zero collisions during live demonstration. Fully battery-powered and untethered.
Islamic University of Madinah, Saudi Arabia
Islamic University of Madinah, Saudi Arabia
5-year program including preparatory year • 136 total units
King Abdullah University of Science & Technology
320-hour intensive computational biology program. Selected participant.
Certificate of Outstanding Achievement — Graduation Project, Faculty of Computer & Information Systems (April 2026)
Recognition for contribution to ABET accreditation renewal process, Faculty of Computer & Information Systems
Participant — KAUST Academy 2025
Central African Republic
Réseau des Jeunes Centrafricains pour le Développement
Certificate of Recognition for community development involvement.
I'm always open to discussing research opportunities, collaborations, or just connecting. Feel free to reach out.
Your message has been received. I'll get back to you as soon as possible.