Frontier AI Security Researcher

Enclosure; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Ownership over research direction

Close collaboration with frontier AI安全

Job summary

Enclosure is seeking an exceptional AI researcher to own a significant part of our AI research as an IC. We value exploration, curiosity, and grit over formal degrees.

You’ll work on frontier AI models, contribute to experiments, and collaborate with security and infrastructure teams to secure increasingly capable systems.

Qualifications include deep ML experience, LM training, peer-reviewed output, and strong coding skills in PyTorch/JAX. AI security interest is highly valued.

Qualifications

• Deep experience in machine learning research, especially frontier AI models.
• Experience training or fine-tuning language or other AI models.
• Rigorous, evidence-driven research with hypothesis testing.

Responsibilities

• Own a significant portion of AI research as an IC.
• Design and run experiments to test hypotheses and evolve findings.
• Collaborate with frontier AI security and infrastructure teams.

Skills

ML Research

LM Fine-tuning

Experiment Design

Publications

Programming

AI Security Interest

Tools

PyTorch

JAX

Job description

Enclosure is seeking an exceptional AI researcher to own a significant part of our AI research as an IC. We value exploration, curiosity, and grit over formal degrees.

You’ll work on frontier AI models, contribute to experiments, and collaborate with security and infrastructure teams to secure increasingly capable systems.

Qualifications include deep ML experience, LM training, peer-reviewed output, and strong coding skills in PyTorch/JAX. AI security interest is highly valued.