Remote Multimodal RL Research Engineer

Tether Ltd.; United States; Remoto; USD 150.000 - 230.000; Tempo pieno

Descrizione del lavoro

Tether Ltd. is seeking a research-oriented AI scientist to join the AI model team, focusing on multi-modal reinforcement learning.

You will design and scale RL architectures for text, image, and audio modalities, and develop training frameworks and reward models for robust, scalable policy learning. You will publish in top-tier conferences and collaborate with engineers to deploy production-grade RL pipelines.

Competenze

• Master's degree in Computer Science or related field; PhD preferred with strong AI research track record.
• Proven experience running large-scale reinforcement learning experiments in multimodal and vision-centric systems.
• Strong publications in top-tier AI conferences (ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV).

Mansioni

• Conduct research on reinforcement learning algorithms for multimodal models, including diffusion-based approaches.
• Design and build reinforcement learning infrastructure for scalable, distributed training across multimodal systems.
• Develop and refine reward modeling strategies to improve training stability and alignment with desired outcomes.
• Create and curate multimodal simulation environments and datasets for robust training and benchmarking.
• Design and conduct benchmarking and evaluation protocols to measure model performance across modalities.
• Analyze and optimize policy performance across modalities by identifying bottlenecks in training and cross-modal alignment.
• Explore next-generation RL paradigms that better learn from environment feedback for superior performance.
• Publish research findings in top-tier conferences such as ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV.

Conoscenze

Multi-modal RL

Reinforcement learning

PyTorch

Research

Formazione

Master's degree in CS

PhD preferred

Strumenti

PyTorch

Descrizione del lavoro

Tether Ltd. is seeking a research-oriented AI scientist to join the AI model team, focusing on multi-modal reinforcement learning.

You will design and scale RL architectures for text, image, and audio modalities, and develop training frameworks and reward models for robust, scalable policy learning. You will publish in top-tier conferences and collaborate with engineers to deploy production-grade RL pipelines.