Remote Multimodal RL AI Research Engineer

Unchain Data; United States; Remoto; USD 120.000 - 190.000; Tempo pieno

Descrizione del lavoro

Tether is seeking a research-driven AI specialist to join the AI model team, focusing on multi-modal reinforcement learning to advance next-generation intelligent systems.

You will design and implement RL architectures that handle text, images and audio, build scalable RL infrastructure, and publish findings at top conferences. This role is remote and global, with high-impact work at the fintech frontier.

Competenze

• Deep expertise in designing multi-modal reinforcement learning systems.
• Experience building RL infrastructures for scalable training.
• Ability to publish research findings in top conferences.

Mansioni

• Conduct research on reinforcement learning algorithms for multimodal models, including diffusion-based approaches for image autoregressive models for multimodal understanding.
• Design and build reinforcement learning infrastructure that supports scalable, distributed training across multimodal systems while maintaining efficiency and reliability.
• Develop and refine reward modeling strategies that improve training stability and mitigate reward hacking.
• Create and curate multimodal simulation environments and datasets to support robust training, evaluation, and benchmarking.
• Design and conduct rigorous benchmarking and evaluation protocols to measure model performance and track progress against baselines.
• Analyze and optimize policy performance across modalities by identifying bottlenecks in training and cross-modal alignment.
• Investigate and develop next-generation reinforcement learning paradigms for improved environment feedback and domain adaptation.
• Publish research findings in top-tier conferences such as ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV.

Conoscenze

Reinforcement learning

Multimodal

RL infrastructure

Reward modeling

Strumenti

PyTorch

TensorFlow

Descrizione del lavoro

Tether is seeking a research-driven AI specialist to join the AI model team, focusing on multi-modal reinforcement learning to advance next-generation intelligent systems.

You will design and implement RL architectures that handle text, images and audio, build scalable RL infrastructure, and publish findings at top conferences. This role is remote and global, with high-impact work at the fintech frontier.