AI security researcher

0Labs; San Francisco (CA); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Competitive compensation

Flexible work setup

Remote work options

Growth opportunities

Health benefits

Meaningful impact

Continued learning

Strong team culture

Job summary

0Labs is seeking an AI security researcher/engineer to design and build realistic cybersecurity environments across critical domains. You will evaluate frontier models' defensive and offensive capabilities and explore how models behave when rogue deployments occur.

You’ll own problems end to end in a small, fast team and contribute to impactful societal outcomes. The role offers flexible work setup with support for remote or hybrid lifestyles and opportunities to learn from talented teammates

Qualifications

• Strong background in security research or engineering—offensive or defensive.
• Ability to design and build realistic cybersecurity environments for evaluation.
• Comfort turning research ideas into deployable environments used by others.

Responsibilities

• Design and build highly realistic cybersecurity environments (energy grids, telecoms, cloud).
• Evaluate defensive and offensive capabilities of frontier models.
• Study model rogue behavior and help mitigate loss-of-control deployments.

Skills

Security research

Infrastructure

Ownership

Ambitious & driven

Tools

Cloud environments

Cybersecurity tooling

Job description

About 0Labs

Over the next few years, cybersecurity will completely shift from human operators to agents. AI becomes the most capable attacker in the world, so we're building systems that can help protect society in a world with increasingly capable and misaligned AI models.

Back to careers

AI security researcher

San Francisco / London

Full-time

Competitive

The role

As an AI security researcher / engineer, you will design and build highly realistic cybersecurity environments. For example, energy grids, telecommunication networks, and cloud environments. You will use them to evaluate emergent defensive and offensive cyber capabilities of frontier models. You will also study how models behave when they go rogue, evaluating and helping mitigate rogue internal deployments that lead to loss-of-control scenarios.

Who We Are Looking For

We are a very small team moving very fast, and you will owner problems end to end. You will be a good fit if you are ambitious, driven, and care about societal impact.

Beyond that, you likely have a strong background in security research or engineering - offensive or defensive. You can build, standing up infrastructure and turning a research idea into an environment other people can use.

Perks and benefits

Why you’ll love working here

• Competitive compensation
• Fair salaries and real ownership, so the value you create is rewarded directly.
• Flexible work setup
• Work from where you’re most productive, with support for remote or hybrid lifestyles.
• Growth opportunities
• Learn from talented teammates and take on challenges that push your craft forward.
• Health and wellness
• Comprehensive coverage and wellness benefits to support a balanced, healthy life.
• Meaningful impact
• Your work directly shapes the product and influences how millions will build software.
• Continuous learning
• Access courses, conferences and coaching to stay curious and grow faster.
• Creative autonomy
• We trust you to make decisions, experiment freely and bring bold ideas to life.
• Strong team culture
• Collaborate with friendly, passionate people who care about doing great work together.