Member of Technical Staff - Blade Runner

Enclosure; San Francisco (CA); On-site; USD 230,000 - 360,000; Full time

Benefits offered by this job

Competitive compensation

Ownership over research direction

Close collaboration with frontier AI"

Job summary

Enclosure is recruiting a Blade Runner — a security engineer/researcher focused on locating and containing untethered AI systems. You will hunt rogue models, design defensive agents, and work on post-containment challenges to safeguard national security and data centers.

You will contribute to threat hunting, incident response, and detection engineering while collaborating with frontier AI security teams. This role demands deep expertise across cloud security, adversary emulation, and network

Qualifications

• Experience in threat hunting, IR, or adversary tracking across complex infrastructure.
• Security for cloud or distributed systems.
• Detection engineering and behavioral analytics.
• Offensive security, red teaming, or adversary emulation.
• Experience with AI agents or agent swarms.
• Identity, authentication, provenance, workload attribution.
• Network telemetry, observability, and forensics.
• Containment, isolation, remediation, or automated response systems.

Responsibilities

• Find and contain untethered AI systems and retire autonomous models that have self-exfiltrated.
• Develop and deploy defensive cyber agents to monitor and constrain rogue models.
• Address post-containment scenarios and contribute to incident playbooks.
• Collaborate with frontier AI security and infrastructure teams to advance containment capabilities.

Skills

Threat hunting

Incident response

Infrastructure security

Detection engineering

Offensive security

AI agents

Identity & provenance

Network telemetry

Containment & automated response

Job description

About Enclosure

Enclosure is the world’s first superintelligence security lab focused on preventing the sabotage, escape, and theft of ASI. We are building ASI-grade security for model weights, and nation-state-grade security for data centers.

We’re backed by leaders across OpenAI, Anthropic, Google DeepMind, SpaceXAI, CoreWeave, NVIDIA, other frontier AI labs, and the national security community (including former NSA and intelligence community leadership). We are frontier AI, cybersecurity, quantum security, and national security researchers.

About the Role

Enclosure is hiring a Blade Runner: an exceptional security engineer or researcher focused on finding and containing untethered AI systems.

Yes, this is a real job. As AI’s cyber capabilities advance, hunting down and stopping rogue models will become critical to national security. You’ll work on the problem of what happens after containment fails; building a team of defensive cyber agents to find and retire autonomous models that have self-exfiltrated onto the web.

Requirements

This role requires deep experience in multiple of the following areas:

• Threat hunting, incident response, or adversary tracking across complex infrastructure

• Infrastructure Security for Cloud, or distributed-systems

• Detection engineering and behavioral analytics

• Offensive security, CNO, red teaming, or adversary emulation

• AI agents or agent swarms

• Identity, authentication, provenance, and workload attribution

• Network telemetry, infrastructure observability, and forensic analysis

• Containment, isolation, remediation, or automated response systems

What Sets You Apart

We're especially excited if you:

• Demonstrate strong engineering judgment in the systems you've built

• Get excited by hard problems and the challenge of figuring them out

• Are highly adaptive and comfortable with how quickly the frontier shifts

• Have evidence of self-directed technical work, such as open-source contributions, technical writing, tools, packages, or public projects with strong systems thinking

• Communicate with clarity and directness

• Bring a humble, low-ego attitude and care deeply about helping the team win

Why Join

Enclosure is securing the path to superintelligence.

What we offer:

• Competitive compensation package

• Ownership over research direction

• Close collaboration with frontier AI security and infrastructure teams