Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this LLM Agent Research Intern role.
Rezi rewrites your resume against Tencent's job description. Free.
Tailor your resume to this LLM Agent Research Intern role.
Rezi rewrites your resume against Tencent's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the LLM Agent Research Intern posting at Tencent — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the LLM Agent Research Intern posting at Tencent — free, in seconds.
About the Role
We are hiring a research intern to train LLM agents that play in-game characters. The agent must stay in persona across multi-turn dialogue, use memory and game context, and maintain relationship, tone, and world rules. The work involves supervised fine-tuning, preference optimization, and reinforcement learning.
Responsibilities
- Train role-play agents with supervised fine-tuning (SFT), then post-train them with direct preference optimization (DPO) and reinforcement learning with verifiable rewards (RLVR).
- Iterate on persona consistency, multi-turn coherence, and instruction following.
- Build and curate SFT, preference, and verifiable-reward data for character dialogue, covering memory injection, relationship stage, language switching, emotion, and out-of-character resistance.
- Design checks that can be verified automatically, such as format, language, persona boundaries, and safety refusals, and use them both as RLVR rewards and as offline regression tests.
- Work with game designers and engineers to bring the agent into a live game, and keep latency, cost, and player experience within production constraints.
Requirements
- Currently enrolled in a Master's or PhD program in Computer Science, NLP, Machine Learning, or a related field, or recently graduated.
- Available at least three days per week, with supervisor and university approval where required.
- Fluent English (written and spoken) and strong communication skills.
- Ability to explain experiment results and trade-offs clearly.
- Hands-on experience with supervised fine-tuning (SFT) of LLMs.
- Experience with post-training methods including DPO and RLVR (or a closely related verifiable-reward RL method).
- Ability to run the loop from data and training config through evaluation and the next iteration.
- Experience training or evaluating role-play or character-dialogue models, including persona consistency, multi-turn dialogue, and staying in character.
- Proficient in Python and PyTorch.
- Comfortable with the Hugging Face / Transformers training stack.
Skills
- Supervised fine-tuning (SFT)
- Direct preference optimization (DPO)
- Reinforcement learning with verifiable rewards (RLVR)
- Persona consistency
- Multi-turn coherence
- Instruction following
- Memory injection
- Relationship stage management
- Language switching
- Emotion expression
- Out-of-character resistance
- Automated verification checks
- Python
- PyTorch
- Hugging Face / Transformers training stack
- LLM agents (memory, planning, or tool use)
- LLM applications in games
Experience Level
- Intern
Education Level
- Master's degree
- PhD
About the Company
- Level Infinite is Tencent’s global gaming brand, offering a comprehensive network of services for games, development teams, and studios worldwide.
- Dedicated to delivering engaging and original gaming experiences to a global audience.
- Building a community that fosters inclusivity, connection, and accessibility.
- Provides a wide range of services and resources to developers and partner studios to help them unlock their games' true potential.
Equal Opportunity
- 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.