大模型评测算法工程师 - Seed Model
Core
Develop evaluation benchmarks and standards for large language models (LLMs) to assess performance, interpretability, and AGI capabilities.
Role type
Senior IC large model evaluation algorithm engineer
Builds
Evaluation benchmarks, red teaming reports, and performance prediction models for Seed Model and related AI applications
Domain
Artificial Intelligence / Large Language Models / AGI Research
Deliverable
production ML models
Required skills
First principles thinking, model evaluation methodology, AGI definition, red teaming, benchmark design, LLM training/evaluation research experience
Preferred skills
Publications in model evaluation or LLM training, experience with interpretability analysis
Technologies
LLMs, MLLMs, Agent Foundation Models, DeepResearch frameworks
Sourced via bytedance · Listed on CareerPlan, which tracks 844,000+ jobs from 20+ sources.