Hone
Member of Technical Staff – Security
SF Office · On-site · Staff · Full-time · Posted Oct 14, 2026
- Experience
- 2+ years, or equivalent depth from research, CTFs, open source or your own projects; time at a fast-growing startup is also required.
- Visa sponsorship
- We sponsor visas and support you through the immigration process.
About the job
Own security for Hone’s long-running AI engines, including their isolation, identity, enterprise controls, and defenses against agent-specific threats.
What you'll do
- Build isolation, network sandboxing, engine identities, scoped credentials, and secret-brokering systems.
- Develop defenses against prompt injection, data exfiltration, and tool misuse; build permissions, approval gates, and action auditing.
- Design security for single-tenant and customer-VPC deployments and develop AI tooling for detection, review, response, and red-teaming.
What they ask for
- 2+ years of security engineering experience, or equivalent depth from research, CTFs, open source or your own projects.
- Time at a fast-growing startup.
- Designed and built security systems from scratch; secured production systems under real load and handled real incidents.
- Strong fundamentals in cloud security, identity and access, networking, isolation, and application security; uses coding agents every day and understands every line shipped.
Nice to have
- Agent or LLM security experience, including prompt injection, sandbox escapes, or red-teaming models or agents.
- Taken an enterprise product through security reviews and audits; CTF background is a plus.
Pay
Competitive salary + meaningful equity.
Tools
RBAC
AI focus
Secure long-running AI agents and engines; build internal AI tooling, including agents that red-team Hone’s engines.
Model-written summary · the original posting is authoritative