About the Role
This role sits at the intersection of cutting-edge AI research and large-scale system engineering, focusing on advancing multi-modal reinforcement learning across text, image, audio, and complex simulated environments. You will contribute to the design of next-generation intelligent systems capable of adaptive decision-making in real-world scenarios. Working in a highly research-driven, globally distributed environment, you will help build and scale reinforcement learning frameworks that power advanced multimodal models. Your work will directly influence model performance, training stability, and reward optimization strategies at scale. You will collaborate with top-tier researchers and engineers to push the boundaries of AI capabilities. The role combines deep theoretical research with hands-on system development and experimentation. It is ideal for someone passionate about foundational AI breakthroughs and real-world deployment impact.
Accountabilities
- Conduct research on reinforcement learning methods for multi-modal systems, including diffusion-based and autoregressive model approaches.
- Design and build scalable RL infrastructure supporting distributed training and evaluation across complex multi-modal environments.
- Develop reward modeling strategies to improve alignment, training stability, and mitigate failure modes such as reward hacking.
- Create and curate simulation environments and datasets for training, benchmarking, and validating multi-modal RL models.
- Design and execute evaluation protocols to measure performance improvements and ensure reproducibility across experiments.
- Analyze model behavior across modalities, identifying bottlenecks in optimization, exploration, and cross-modal alignment.
- Explore and develop next-generation RL paradigms to enhance learning from environment feedback and improve SOTA performance.
- Publish research in leading AI conferences such as NeurIPS, ICML, ICLR, CVPR, and related venues.
Requirements
The ideal candidate has a strong academic and practical background in machine learning, reinforcement learning, and multi-modal AI systems, with a proven record of research excellence and scalable system development. You are comfortable working at the frontier of AI research while building production-grade experimentation pipelines.
- Master’s degree in Computer Science or related field required; PhD preferred in ML, CV, NLP, or AI-related disciplines.
- Strong publication record in top-tier AI conferences (NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV).
- Proven experience in large-scale reinforcement learning experiments, particularly in multi-modal or vision-centric systems.
- Deep understanding of reinforcement learning theory, optimization, and policy learning in high-dimensional environments.
- Strong hands-on experience with PyTorch and deep learning frameworks for multimodal AI systems.
- Experience building end-to-end RL pipelines including simulation, training, evaluation, and deployment.
- Ability to address core RL challenges such as sample efficiency, exploration-exploitation trade-offs, and training stability.
- Strong analytical and problem-solving skills with a research-driven, experimental mindset.
Benefits
- Competitive compensation package aligned with top-tier AI research talent
- Fully remote, global-first work environment
- Opportunity to work on frontier AI research problems at scale
- High-impact role influencing next-generation multimodal intelligence systems
- Collaboration with leading researchers and engineers in AI and reinforcement learning
- Access to large-scale experimentation infrastructure and research resources
- Strong culture of innovation, autonomy, and research publication support