Hunyuan Multimodal Reinforcement Learning (rl) Research Intern
Tencent Cloud
Capitasky, Singapore
Reinforcement learning algorithms
Multimodal model research
Deep learning system implementation
The role involves conducting research on reinforcement learning algorithms for multimodal models including diffusion and autoregressive models
Job Summary
The role involves conducting research on reinforcement learning algorithms for multimodal models including diffusion and autoregressive models.
Responsibilities include designing and developing reinforcement learning infrastructure and reward modeling strategies to improve training efficiency and stability.
Tencent Cloud fosters an environment where diverse voices fuel innovation and supports employees to achieve individual and common goals.
Matching Summary
The role involves conducting research on reinforcement learning algorithms for multimodal models including diffusion and autoregressive models.
Skills & Requirements
Must-have
Reinforcement learning algorithms
Multimodal model research
Deep learning system implementation
Model training and inference optimization
CPU/GPU acceleration
Distributed training and inference
Nice-to-have
Experience with diffusion models
Experience with autoregressive models
Text-to-image or text-to-video generation
Participation in ACM/NOIP
Key Requirements
Currently enrolled PhD student
Strong research capability with top-tier publications
Programming skills in deep learning and distributed systems