大模型评测工程架构师 - Seed Model
Core
Building the engineering infrastructure for evaluating large language models, multimodal models, and agents.
Role type
Senior IC machine-learning engineering architect (evaluation systems)
Builds
Scalable evaluation platforms and frameworks for text, multimodal, and agent models
Domain
Artificial Intelligence / Large Language Models / Evaluation Engineering
Deliverable
production ML models
Required skills
Python, Go, distributed systems, task orchestration, environment isolation, failure recovery, resource governance, HDFS, Ray, message queues
Preferred skills
Large model deployment workflows, MLLM, GenMedia, AI for Science, robotics
Technologies
Python, Go, HDFS, Ray, message queues
Responsibilities
Design and implement key engineering capabilities for model evaluation (scheduling, concurrency, isolation, retry, cost optimization); Design platforms supporting stable execution of diverse evaluation tasks; Explore and advance frontier engineering technologies for large models.