LLM Agent Evaluation Engineer — Build Intelligent Agents

ByteDance Applied Machine Learning Ark team in San Jose develops and operates LLM service platforms that offer MaaS solutions to businesses and researchers, spanning model serving, tool calling, and analytics.

This full-time role emphasizes designing evaluation systems for LLM agents, building benchmarks and pipelines, analyzing traces and feedback, and collaborating with research, platform, and product teams to bring methods into production.