Stage - AI Agent Evaluation for Simcenter Amesim m/f - Strategic Student Program
Core
Design and develop an evaluation platform to analyze, compare, and automate the validation of AI agent workflows and MCP-based interactions with Simcenter Amesim APIs using Large Language Models.
Role type
AI Agent Evaluation Engineer (Intern)
Builds
Evaluation platform for AI workflows and MCP integrations
Domain
Industrial software simulation (Simcenter Amesim) + AI/LLM
Deliverable
production ML models
Required skills
Python, Go, LLM integration, test suite design, CI/CD practices, performance analysis
Preferred skills
MCP (Model Context Protocol) knowledge, MLflow experience
Technologies
Simcenter Amesim, Python, Go, LLMs, MLflow, CI/CD
Responsibilities
Design and implement test suites to measure AI agent performance; Develop an automated evaluation platform; Integrate LLM-based techniques for result validation; Adapt to evolving technological priorities.
Seniority
Intern
