大模型评测工程师（J98467）
Core
Design and develop multimodal evaluation and data annotation platforms, building high-performance, scalable AI systems.
Role type
Senior full-stack engineer (LLM evaluation & multimodal platforms)
Builds
Multimodal evaluation platforms, multimodal data annotation platforms
Domain
Artificial Intelligence / Large Language Models / Multimodal AI
Deliverable
production ML models
Required skills
Large language model training, LLM evaluation, system design, full-stack development, machine learning, deep learning, distributed storage and computing, task scheduling, concurrency handling, data consistency
Preferred skills
LLM development, LLM application
Technologies
N/A
Responsibilities
Design and develop multimodal evaluation and data annotation platforms; Solve complex engineering challenges in task scheduling, concurrency, data consistency, and distributed systems; Collaborate with algorithm and product teams to translate business needs into technical solutions; Research and integrate industry-leading technologies to optimize evaluation and annotation workflows.
Seniority
Senior, hands-on IC