[expression Of Interest] Research Scientist / Engineer, Honesty
Anthropic
New York City, NY, USA
$350,000 - $500,000 usd py
On-site
Language model finetuning
Classifier training
Experimental design
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society
Job Summary
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society.
Responsibilities include designing data curation pipelines, developing classifiers for hallucinations, creating honesty benchmarks, and implementing techniques to ground model outputs.
The company offers competitive compensation, generous vacation and parental leave, flexible working hours, and a collaborative research environment focused on high-impact AI safety.
Matching Summary
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society.