Nicholas Carlini
Research Scientist · Anthropic
At a glance. Nicholas Carlini is listed as Research Scientist at Anthropic. The profile sits among the builders and open-source contributors. Fields listed: Safety and alignment, Evaluation and benchmarks and Language models. The source lists 2 official pages, 8 listed honors and open-role pages for Anthropic.
Summary
Research scientist at Anthropic working on machine learning security; formerly at Google Brain and DeepMind.
Known for: Extracting Training Data from Large Language Models; Stealing Part of a Production Language Model; Yet Another Applied LLM Benchmark.
Works at
- Anthropic 34 people in the wiki
Other documented roles
Not confirmed as current in the source profile.
- Research scientist (2023–2025), DeepMind
- Research scientist (2018–2023), Google Brain
Open roles
Related people
- Samuel R. BowmanAlso at Anthropic
- Collin BurnsAlso at Anthropic
- Ethan PerezAlso at Anthropic
- Eugene YanAlso at Anthropic
- Rohan TaoriAlso at Anthropic
- Saadia GabrielLanguage models · Safety and alignment
- Margaret MitchellSafety and alignment · Evaluation and benchmarks
- Diogo AlmeidaLanguage models · Evaluation and benchmarks
- Aylin CaliskanSafety and alignment · Evaluation and benchmarks
- Yulia TsvetkovLanguage models · Safety and alignment
Source and corrections
Read the full profile on USASI ↗
Facts on this page come from that USASI profile (reviewed Oct 21, 2026); data last checked Oct 23, 2026. See something wrong? Suggest a correction.