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.
• Create and curate multimodal simulation environments and datasets to support robust training, evaluation, and benchmarking of reinforcement learning systems.
• Design and conduct rigorous benchmarking and evaluation protocols to measure model performance, track progress against baselines, and validate improvements across multimodal tasks.
• Analyze and optimize policy performance across modalities by identifying bottlenecks in training, credit assignment, and cross-modal alignment.
• Investigate and develop next-generation reinforcement learning paradigms that more effectively learn from environment feedback, with the goal of achieving superior state-of-the-art (SOTA) performance.
• Publish research findings in top-tier conferences such as ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV etc.
• A Master's degree in Computer Science or a related field is required; a PhD in Machine Learning, NLP, Computer Vision, or a closely related discipline is preferred, along with a strong track record of AI research and publications in top-tier conferences.
• Proven experience running large-scale reinforcement learning experiments in multimodal and vision-centric systems, including online RL settings, with demonstrated impact on domain-specific decision-making and measurable improvements in policy performance.
• Deep understanding of reinforcement learning algorithms and optimization methods applied to vision and multimodal learning problems, with a focus on improving policy stability, exploration, and sample efficiency in complex, high-dimensional environments involving images, video, and other modalities.
• Strong proficiency in PyTorch and deep learning frameworks for vision and multimodal AI, with hands-on experience building end-to-end RL pipelines covering simulation, training, evaluation, and deployment in production-grade systems.
• Demonstrated ability to apply empirical research to solve core RL challenges in multimodal and vision tasks, such as sample inefficiency, exploration-exploitation tradeoffs, and training instability, along with experience designing robust evaluation frameworks and iterating on algorithmic improvements to advance agent performance.
• Proven track record of research publications in top-tier conferences such as ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV etc.