Hunyuan Multimodal Reinforcement Learning (RL) Research Intern
Tencent Open · verified Oct 22, 2026 At a glance
Junior AI Research role at Tencent. Singapore-CapitaSky · full-time.
Pay not stated AI Research salary
aimlroles summary, based on the employer's posting.
What you'll do
- Investigate reinforcement-learning methods for multimodal generation and understanding, including diffusion and autoregressive models
- Build training infrastructure and reward models to support large-scale learning, improve stability, and reduce reward hacking
- Test reinforcement-learning approaches that learn more directly from feedback provided by an environment
What you bring
- You are pursuing a PhD in computer science or a closely related discipline
- Your research record includes papers at leading venues such as ICML, NeurIPS or another listed conference
- You can implement deep-learning systems and optimize model training, inference, CPU/GPU acceleration and distributed workloads
- You have hands-on experience with diffusion, autoregressive or text-to-image generation models
Who this fits
This internship suits a doctoral researcher with strong implementation skills and a track record of conference research. The role is based in Singapore.
From the employer
Business Unit
Technology Engineering Group (TEG) is responsible for supporting the company and its business groups on technology and operational platforms, as well as the construction and operation of R&D management and data centers, TEG provides users with a full range of customer services. As the operator of the largest networking, devices, and data center in Asia,TEG also leads the Tencent Technology Committee in strengthening infrastructure R&D through internal and distributed open source collaboration, constructing new platforms and supporting business innovation.What the Role Entails
1. Conduct research on RL algorithms for multimodal models, including diffusion models for image, video, and 3D generation, autoregressive models for multimodal understanding, and potentially unified multimodal frameworks.
2. 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.
3. Explore next-generation RL paradigms that more directly and effectively learn from environment feedback.
Who We Look For
1. Currently enrolled as a PhD student in Computer Science or a closely related field.
2. Demonstrated strong research capability, with publications in top-tier conferences such as ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, SIGGRAPH.
3. Strong hands-on programming skills, with solid experience in deep learning system implementation, model training and inference optimization, CPU/GPU acceleration, and distributed training and inference.
4. Prior experience with diffusion models, autoregressive models, and/or text-to-image or text-to-video generation is highly preferred.
5. Participation in ACM/NOIP is a strong plus.
Equal Employment Opportunity at Tencent
As an equal opportunity employer, we firmly believe that diverse voices fuel our innovation and allow us to better serve our users and the community. We foster an environment where every employee of Tencent feels supported and inspired to achieve individual and common goals.