Large Model Application Algorithm Research Scientist-International Content Security Algorithm Research-Soaring Star Talent Program
Summary
Research scientist role focused on deploying and optimizing large models for real-world applications, with a focus on content security and reinforcement learning. Core work includes designing reward models, improving reasoning efficiency, and advancing reasoning stability in AI systems.
- Deploy large models for real world applications
- Design reward models for reinforcement learning
- Develop content safety machine learning models
- Evaluate model reasoning performance across tasks
- Improve reinforcement learning training stability
- Optimize reasoning efficiency using knowledge distillation
- Research reasoning optimization for large language models