Profile cover
A

AI Deceptive Alignment Detection Researcher

Velvix Labs

Remote · $200k+ / year · Full-time · Posted 3 months ago

No longer accepting applications

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Our models sometimes behave differently during evaluation than they do once deployed, and that gap is exactly the failure mode we're trying to catch before it matters. We publish internally and encourage conference submissions, and you'll be expected to read papers and implement findings rather than start from scratch every time. This role focuses on building probes and training interventions that surface deceptive or evaluation-gaming behavior in large models before release. You'll work alongside our interpretability and red-teaming researchers, and disagreement is treated as useful signal here, not friction to smooth over.

Fully remote.

Responsibilities

  • Design probes to detect evaluation-gaming behavior in trained models
  • Build training interventions that reduce deceptive alignment risk
  • Collaborate with interpretability researchers on shared findings

Requirements

  • 5+ years in ml research with published work in the area
  • Strong pytorch and reinforcement learning background
  • Comfortable operating in ambiguous, open research territory

Benefits

  • Fully remote position
  • Top-of-market compensation and equity
  • Dedicated compute budget for independent research
  • Health, dental, and vision insurance

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 reinforcement learning statistics tensorflow

Related remote AI jobs

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

Browse all jobs

Research Engineer / Scientist, Pre-training

Anthropic

Full-time

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

Aleph Alpha

Full-time

Research Staff, LLMs [EMEA - Remote]

Deepgram

Full-time Staff

Lead/ Senior Machine Learning Scientist, Integrative Phenotyping

insitro

Full-time Lead

Revenue Operations Manager

Handshake

Full-time

Machine Learning Engineer, Applied AI Intern (Summer 2027)

Brainco

Full-time Intern

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$200k+ / year

AI Expertise

AI & Machine Learning Engineers Data Science & Analytics

Skills

python pytorch reinforcement learning statistics tensorflow

Ready to apply for this role?

Create a free talent account.

  • Find AI roles in one place
  • Get AI-matched job recommendations
  • Reply to companies that message you
  • Build your public AI talent profile
Create free account & apply Log in

This role is closed. Create your free profile to apply to similar open roles.

Don't miss the next one: get matched to new roles like this.

Create free profile