CU

AI Lab - LLM Applied Evaluation and Benchmark Intern

Cummins

Beijing · Posted Aug 31

Data Onsite
Apply now

Internship at Cummins AI Lab focusing on evaluating and benchmarking Large Language Model (LLM) applications, including Chatbot and ChatBI systems, in automotive and industrial domains. Responsibilities include designing and executing evaluation frameworks, building benchmarking datasets and metrics, testing AI Agents in real-world scenarios, analyzing and improving model behavior, performing data cleaning/anonymization/masking for privacy, and writing evaluation reports for stakeholders.

What they are looking for

Test_case_design Boundary_testing Logical_validation Data_cleaning Anonymization

Details

Work type
Onsite

Get new Data internships by email

Free daily digest, matched to what you pick. Unsubscribe anytime.