Level Infinite, Tencent’s global gaming brand, is seeking a research intern to train LLM agents that play in-game characters. The role emphasizes supervised fine-tuning, DPO, and RLVR, with deployment in a live game and production constraints.
You will build SFT, preference, and verifiable-reward data for character dialogue, ensure persona consistency across multi-turn dialogue, and work with game designers and engineers to achieve smooth integration.
#J-18808-Ljbffr
