Skip to main content

Research Fellowship Mechanistic Interpretability Jobs - Hiro

Browse 12+ Research Fellowship Mechanistic Interpretability roles from companies hiring right now. Updated daily as new jobs land on Hiro. Salaries range from $0K to $0K based on listed pay.

12 Research Fellowship Mechanistic Interpretability roles

Sorted by most recently posted.

Ntu logo

Research Fellow (Cryptography and/or machine learning interpretability)

Ntu · Ntu Main Campus, Singapore

CryptographyMachine Learning
Today
Ntu logo

Research Fellow (Cryptography and/or machine learning interpretability)

Ntu · Ntu Main Campus, Singapore

CryptographyMachine Learning
Today
Crowdstrike logo

Director, AI Alignment and Interpretability (Remote)

Crowdstrike · Remote

LeadershipLeanMachine Learning+1
1w ago
Output logo

Member of the Technical Staff, Interpretability

Output · New York Hq 🗽

LeadershipMachine LearningPython+1
2w ago
Apple logo

AIML - Research Scientist, AI Interpretability & Visualization

Apple · Cambridge, MA

Machine LearningPrototypingSAFe
1mo ago
Vmax logo

Member of Technical Staff - Mechanistic Interpretability

Vmax · San Francisco

$300K–$500K/yr

LLMsMachine LearningPython+2
1mo ago
Vmax logo

Research Fellowship - Mechanistic Interpretability

Vmax · San Francisco

LLMsMachine LearningPython+2
1mo ago
Anthropic logo

[Expression of Interest] Research Manager, Interpretability

Anthropic · San Francisco, CA

LeadershipSAFe
2mo ago
Anthropic logo

Research Scientist, Interpretability

Anthropic · San Francisco, CA

LLMsPythonSAFe
2mo ago
Anthropic logo

Research Engineer, Interpretability

Anthropic · San Francisco, CA

JavaLLMsPython+1
2mo ago
Ctgt logo

Machine Learning Engineer: LLM Interpretability & Systems

Ctgt · San Francisco

$175K–$250K/yr

Deep LearningDockerGenerative AI+1
2mo ago
Openai logo

Researcher, Interpretability

Openai · San Francisco

ComplianceDeep LearningMachine Learning+2
6/15/2025

Explore more research fellowship mechanistic interpretability roles

Tired of scrolling job boards?

Hiro scores every research fellowship mechanistic interpretability role against your profile so you only see the ones that actually fit. Free to start.