AI Agent效果优化工程师-Aime
Core
Build and optimize AI Agent performance across business scenarios through a closed loop of evaluation, root cause analysis, strategy tuning, and validation.
Role type
Senior AI Agent Effectiveness Engineer
Builds
AI Agent products and their performance in complex multi-task business scenarios
Domain
Artificial Intelligence / Large Language Models (LLM) / Agent Systems
Deliverable
production ML models
Required skills
LLM/Agent development and evaluation, Prompt Engineering, RAG optimization, Root Cause Analysis, automated evaluation tool development, API debugging, data analysis, workflow orchestration
Preferred skills
Experience with complex business scenarios, reverse engineering competitor products, iterative methodology development
Technologies
LLMs, RAG, Prompt Engineering, Workflow Orchestration, API
Responsibilities
Build high-coverage evaluation datasets and acceptance criteria for Agents; conduct high-frequency effect experiments to tune performance; analyze daily Agent operations and translate insights into technical solutions; track and deconstruct industry-leading Agent products to inform strategy; iterate evaluation standards and optimization linkages.
Seniority
Senior, hands-on IC
