大模型算法工程师（评测方向）-抖音研发（北京/杭州/深圳/上海）
Core
Design and implement large model evaluation technologies for actual business scenarios, building frameworks and models to analyze performance and support iteration.
Role type
Senior IC large model algorithm engineer (evaluation)
Builds
Evaluation frameworks, evaluation models, and evaluation systems for LLMs, multimodal understanding/generation, Agents, and world models.
Domain
Artificial Intelligence / Large Language Models / Multimodal AI
Deliverable
production ML models
Required skills
Machine learning, deep learning, natural language processing, Python, evaluation framework design, model training and deployment, problem analysis
Preferred skills
Experience with LLMs, multimodal understanding/generation, Agents, world models, autonomous exploration of solutions
Technologies
Python, LLMs, multimodal models, Agents, world models
Responsibilities
Design and implement evaluation technologies for business scenarios; design evaluation frameworks and train/deploy evaluation models; analyze model performance and attribute problems; explore scientific and scalable evaluation methodologies; research and apply cutting-edge AI technologies to evaluation work.