ML Research Engineer specializing in Multi-Agent Reinforcement Learning, Goal-Conditioned RL, and Curriculum Learning
I'm a Machine Learning Research Engineer passionate about advancing the field of Multi-Agent Reinforcement Learning. My work focuses on developing algorithms that enable agents to learn complex behaviors through goal-conditioned learning and curriculum strategies.
Currently at InstaDeep working with the Mava team on cutting-edge MARL research. I hold a Master's degree from AIMS South Africa through the AI for Science program in partnership with DeepMind.
Multi-Agent RL • Goal-Conditioned RL • Contrastive Learning • Curriculum Learning • LLM Agents
JAX • Python • PyTorch • TPU/GPU • Distributed Systems
InstaDeep
Working with the Mava team on multi-agent reinforcement learning research. Developing novel approaches combining contrastive learning, goal-conditioned RL, and curriculum learning for complex multi-agent environments.
AIMS South Africa
AI for Science program in partnership with DeepMind. Focused on reinforcement learning, deep learning, and their applications to scientific problems.
A selection of my original research and engineering projects
Fine-Grained Credit Assignment for RL Training. Token-level reward assignment to improve training stability and sample efficiency for LLMs.
Combining contrastive reinforcement learning with unsupervised environment design for multi-agent curriculum learning.
Automatic tree search LLM-based agent for code generation and problem solving with intelligent exploration.
Detecting GenAI-generated content and sophisticated manipulation in public media using machine learning.
Supervised fine-tuning experiments on DeepSeek-7B for specialized task performance.
Benchmarking inference time scaling strategies on MLE-bench. Measuring how well AI agents perform at ML engineering.
AIDE: The Machine Learning CodeGen Agent. Automated ML engineering through intelligent code generation.
Neural machine translation system for Arabic to Swahili, addressing low-resource language pair challenges.
I'm always interested in discussing research collaborations, new opportunities, or just chatting about RL and AI.