AI Research Engineer (Multi-Modal Reinforcement Learning)

Tasks

• Analyze model behavior across modalities
• Build scalable reinforcement learning infrastructure
• Create simulation environments and datasets
• Design evaluation protocols
• Develop reward modeling strategies
• Explore next-generation reinforcement learning paradigms
• Publish research in AI conferences
• Research reinforcement learning methods for multi modal systems

Perks/Benefits

• Autonomy
• Fully remote
• Global First Work Environment
• Innovation culture
• Research infrastructure access
• Research publication support

Skills/Tech-stack

Autoregressive models | Deep learning | Diffusion Models | Distributed Training | Evaluation | Machine Learning | Multi-Modal | Multi-modal AI | Optimization | Policy learning | PyTorch | Reinforcement Learning | Reward Hacking | Reward Modeling | Simulation