Remote AI Research Engineer: Multimodal RL

Tether; United Kingdom; Remote; GBP 90,000 - 140,000; Full time

Job summary

Tether is seeking an AI scientist to join the AI model team, driving innovation in multi-modal reinforcement learning to advance next-generation intelligent systems. You will focus on improving decision-making and adaptive behavior across text, images and audio, delivering robust performance for real-world challenges.

You will design and scale RL infrastructure, develop reward models, curate datasets, and benchmark progress across modalities.

Qualifications

• Deep expertise in designing multi-modal reinforcement learning systems.
• Hands-on, research-driven approach to building algorithms and training frameworks.
• Experience with diffusion-based and autoregressive multimodal models.

Responsibilities

• Research RL algorithms for multimodal models, including diffusion-based approaches for image autoregressive models and unified multimodal frameworks.
• 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, align model behavior with desired outcomes, and mitigate reward hacking and related failure modes.
• Create and curate multimodal simulation environments and datasets to support robust training, evaluation, and benchmarking of RL systems.
• Design and conduct rigorous benchmarking and evaluation protocols to measure model performance, track progress against baselines, and validate improvements across modalities.

Tools

Diffusion models

Autoregressive models

RL infrastructure

Job description

Tether is seeking an AI scientist to join the AI model team, driving innovation in multi-modal reinforcement learning to advance next-generation intelligent systems. You will focus on improving decision-making and adaptive behavior across text, images and audio, delivering robust performance for real-world challenges.

You will design and scale RL infrastructure, develop reward models, curate datasets, and benchmark progress across modalities.