Member of Technical Staff
Enclosure.inc
Member of Technical Staff
Enclosure.inc
Research lab securing artificial superintelligence containment
Enclosure is the world’s first superintelligence security lab focused on preventing the sabotage, escape, and theft of superintelligence. We’re backed by leaders across OpenAI, Anthropic, Google DeepMind, SpaceXAI, NVIDIA, and the national security community, including former NSA and intelligence community leadership.
Enclosure is hiring an experienced CNE tool developer, rootkit designer, or offensive cyber researcher. In this role, you will develop new and novel techniques to steal and compromise model weights and test our efforts to protect them. Enclosure is building frontier security systems to prevent sophisticated attackers from getting into data centers and AI models from getting out. Enclosure is advised by IC leaders, and the founding team comes from frontier AI, quantum security, cybersecurity, and national security. If you’re asking yourself how we can secure the stack and protect America’s infrastructure in the next 6-12 months, we should chat.
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
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
Research lab securing artificial superintelligence containment
Enclosure Inc. focuses on security and containment of artificial superintelligence (ASI). It secures AI model weights and builds nation-state–level security for AI data centers, using bidirectional containment to protect models from external attacks and to prevent rogue AI from escaping. The company differentiates itself by its explicit bidirectional containment approach and ties to major AI players and national-security communities. Its goal is to reduce the risk posed by highly capable AI by preventing misuse, leakage, or uncontrolled growth.
Explore more opportunities at Enclosure.inc