Profile cover
A

AI Scalable Oversight Research Engineer

Aria Watanabe

Full-time · Job · Los_Angeles

About the role

The core problem of AI safety isn't aligning today's systems — it's maintaining alignment as capabilities scale. Scalable oversight is one of the most promising research directions for that problem: using AI assistance to help humans evaluate AI behavior even when human understanding is the bottleneck. Debate, amplification, recursive reward modeling — these are the frameworks we're building on, and we need a senior researcher who can move them from academic papers to working systems. You'll design and run experiments testing whether scalable oversight protocols actually improve the quality of human evaluations of complex AI behavior. That means building evaluation harnesses, constructing tasks where evaluator mistakes are detectable, measuring how different oversight protocols affect evaluator accuracy, and publishing findings that advance the field's understanding of what works at scale. This is a pure research role at a lab that's deeply committed to publishing openly. Your work will be read by the safety community. You'll have significant research autonomy, access to frontier model APIs, and a direct line to our technical leadership who engages seriously with your research agenda.

Responsibilities

  • Design and run experiments evaluating scalable oversight protocols in practice
  • Build evaluation harnesses for tasks where human evaluator errors are detectable
  • Measure how oversight protocols affect evaluator accuracy on complex AI behavior
  • Implement debate, amplification, and recursive reward modeling variations
  • Publish findings in AI safety and ML conferences
  • Collaborate with alignment researchers across the broader community

Requirements

  • 6+ years in ML research with AI safety, alignment, or evaluation focus
  • Deep understanding of scalable oversight research literature
  • Strong Python and PyTorch skills with experiment infrastructure experience
  • Publication record at NeurIPS, ICML, or AI safety venues
  • Independent research judgment with ability to define and pursue a research agenda

Benefits

  • Fully remote with complete schedule flexibility
  • Top-of-market compensation
  • Uncapped research budget for experiments
  • Full open publication policy
  • Sabbatical program after 2 years

Keep exploring related roles

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

Categories

AI & Machine Learning Engineers AI Product & Strategy

Skills

python pytorch hugging face statistics docker

Related remote AI jobs

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

Browse all jobs

Senior Product Security Engineer

RemoteAI company

Full-time Senior

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

RemoteAI company

Full-time Senior

Drone Platform Integration & Network Support Engineer

RemoteAI company

Full-time

AI Resident UK/EMEA

RemoteAI company

Full-time

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

RemoteAI company

Full-time Senior

Senior Machine Learning Engineer (Clinical Team)

RemoteAI company

Full-time Senior

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$200k+ / year

AI Expertise

AI & Machine Learning Engineers AI Product & Strategy

Skills

python pytorch hugging face statistics docker 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