Auditor / Research Lab Assistant
Contributing to a project on robustifying autonomous vehicles by benchmarking reinforcement learning algorithms across simulation environments. The work spans setting up simulation infrastructure, running baseline RL experiments, comparing results across algorithms, and writing up the technical process so it’s reproducible.
Most of my time goes into moving research code from a local setup into headless and cloud environments using Nautilus, Kubernetes, CARLA, and Python. The end goal is a benchmarking framework that compares multiple RL algorithms cleanly, with weekly deliverables, documentation, and status updates along the way.
- AI research
- Reinforcement learning
- Autonomous vehicles
- CARLA
- Kubernetes
- Nautilus
- Python