AI Research Engineer (Multi-Modal Reinforcement Learning) - 100% Remote Worldwide

About the job

As a member of the AI model team, you will drive innovation in multi-modal reinforcement learning to advance next-generation intelligent systems. Your work will focus on optimizing decision-making and adaptive behavior across integrated data modalities such as text, images and audio to deliver enhanced intelligence, robust performance, and domain-specific capabilities for real-world challenges. You will develop and scale reinforcement learning techniques within complex multi-modal architectures, including diffusion-based generative models and autoregressive models for multimodal understanding, as well as resource-efficient models designed for constrained hardware environments. This includes conducting research on reinforcement learning algorithms for multimodal models, spanning diffusion models for image autoregressive models for multimodal reasoning, and unified multimodal frameworks.

You are expected to have deep expertise in designing multi-modal reinforcement learning systems and a strong background in advanced model architectures, with a hands-on, research-driven approach to building and deploying novel algorithms and training frameworks. You will design and develop RL infrastructure and reward modeling strategies to enable efficient large-scale training, improve training stability, and mitigate reward hacking and related failure modes. Your responsibilities also include curating multi-modal simulation environments and training datasets, improving baseline policy performance across modalities, and identifying and resolving bottlenecks in multi-modal learning and reward optimization. In addition, you will explore next-generation reinforcement learning paradigms that more directly and effectively learn from environment feedback, with the goal of unlocking superior, domain-adapted AI performance in dynamic, real-world environments.

Responsibilities

• Conduct research on reinforcement learning algorithms for multimodal models, including diffusion-based approaches for image autoregressive models for multimodal understanding, and unified frameworks that integrate multiple modalities.

• 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.