视频生成算法工程师 (Reward Model)
北京、深圳、上海
全职
研发 - 算法
职位描述
负责视频生成 reward model、benchmark 和评测、迭代体系建设，把主观视频质量拆解成可训练、可评测、可追踪的多维信号： 1. 与数据团队合作，制定和把控视频生成打分标准。 2. 对音视频理解专家模型进行质量评估、bad case 收集和持续迭代，如ASR、说话人、音色、语种、音效、音画同步等音频专家模型，以及OCR、目标检测、动作识别、切镜点检测、镜头运动估计等视觉专家模型。 3. 训练多维 reward model，包括视觉 RM、音视频 RM、语义遵循 RM、美学 RM、崩坏判定模型等。 4. 建立 benchmark 和自动评测 pipeline，结合人工评测、专家模型交叉验证 RM 准确度。 5. 发现 benchmark 被 hack、RM 偏置和评测失真问题，持续优化评测可信度。 6. 为后训练、数据清洗、模型选型和交付版本提供依据，并结合评测反馈、用户数据，持续迭代 RM。
职位要求
投递
We are the first General World Model ("GWM") company globally that built a GWM unifying the digital world and the physical world. We are dedicated to building a unified intelligence framework capable of modeling, reasoning, predicting and acting upon the underlying rules that govern both digital and physical worlds. Guided by first principles thinking, we use visual and auditory information, which naturally encodes the physical world, to train our foundation world model and replicate the human process of perceiving, simulating and interacting with the world, and ultimately, to enable AGI that connects the digital world with the physical world.
