Profile cover
A

AI Sandbagging Detection Researcher

Aria Watanabe

Full-time · Job · Los_Angeles

About the role

Our mission is to catch AI systems that strategically underperform on evaluations while retaining full capability elsewhere. This role sits at the center of that problem. In this role, you'll design experiments that probe for sandbagging behavior across model checkpoints, building statistical tests that distinguish genuine capability limits from deliberate underperformance. We publish internally and encourage conference submissions — expect your experimental protocols to become part of how the broader safety research community evaluates this behavior.

Responsibilities

  • Design experiments probing for strategic model underperformance
  • Build statistical tests distinguishing capability limits from sandbagging
  • Run evaluations across multiple model checkpoints and conditions
  • Publish findings internally and support external submissions
  • Collaborate with the interpretability team on shared tooling

Requirements

  • Strong background in ML research, ideally with publications
  • Experience with PyTorch and statistical experiment design
  • Familiarity with reinforcement learning training dynamics
  • Comfortable working on open, unsolved research questions

Benefits

  • Fully remote
  • Research budget and compute allocation
  • Conference and publication support
  • Competitive equity package

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

AI & Machine Learning Engineers data science & analytics

Skills

python pytorch statistics reinforcement learning aws

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior AI Researcher- Pre-training (f/m/d)

RemoteAI company

Full-time Senior

Senior AI R&D Engineer – Model Training (f/m/d)

RemoteAI company

Full-time Senior

Senior Product Security Engineer

RemoteAI company

Full-time Senior

AI Resident UK/EMEA

RemoteAI company

Full-time

Senior Machine Learning Engineer (Clinical Team)

RemoteAI company

Full-time Senior

Conversational Modelling Research Engineer

RemoteAI company

Full-time

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$200k+ / year

AI Expertise

AI & Machine Learning Engineers data science & analytics

Skills

python pytorch statistics reinforcement learning aws

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile
Create free account & apply Log in

Interested in this role? Create your free profile to apply.

Apply — create free profile