Research Engineering Intern, AI Evaluations
Core
Build and run AI model evaluations to measure performance in underrepresented languages and contexts, preparing datasets, running inference, and analyzing results.
Role type
Research Engineering Intern (AI Evaluations)
Builds
Evaluation pipelines, annotation tasks, and technical reports for AI model benchmarks
Domain
AI safety & alignment, multilingual NLP, low-resource languages
Deliverable
production ML models
Required skills
Python, data analysis (pandas), LLMs, API integration, probability & statistics, debugging
Preferred skills
ML evaluation/annotation experience, speech/multilingual NLP, GPU inference, cloud tooling, Android/app debugging
Technologies
Python, pandas, LLM APIs, cloud tooling, Android
Responsibilities
Prepare datasets and run model inference; monitor live evaluations and triage issues; run automated quality checks; compute agreement scores and support experiments; build and maintain tooling for data processing and analysis
Seniority
Intern