Sr. Security Engineer, AI Security
New York City, NY, United States21h ago
Key details
- Location
- New York City, NY, United States
- Work style
- Onsite
- Level
- Senior
- Job type
- Full-time
- Experience
- 5–7 yrs
- Function
- Software engineering
- Focus area
- AI / ML
- Posted
- 21h ago
Skills
About the role
Beacon is looking for a Sr. Security Engineer, AI Security to own the safe use of AI at Beacon and across the companies in our portfolio. You will design and operate the security controls, harden the systems that AI tools and agents connect to, and work closely with engineering on identity, authorization, and network protections for AI agents and other non-human workloads.
Key Responsibilities
Give every agent an owner, scoped credentials, least privilege, and approvals where the action calls for it, and track it from creation to offboarding like a user.
Own the security requirements for AI integrations (MCP connections, OAuth grants), memory, and retrieval, and set tenant defaults and approved connectors.
Keep a live view of AI tools and agents, including AI features that vendors turn on inside tools we already use.
Put limits on tool calls, network access, data egress, and resource use.
Threat model and adversarially test our internal AI platform and agents, covering prompt injection, data disclosure, unsafe tool use, and unauthorized actions. Turn findings into regression tests and release gates.
Define the logs AI systems must produce, build detections for risky grants and sensitive data going into AI tools, lead the AI side of incidents, and join the on-call rotation.
Give a quick yes with conditions on new tools, and keep approved patterns and a pre-cleared list so most requests need no review.
Add an AI inventory and the same standards to the security baseline for each acquisition.
What we are looking for
About 5 to 7 years in security engineering, application security, or cloud security.
Hands-on experience securing LLM applications, agents, or AI developer tools, including prompt injection, data leakage, excessive agency, and insecure tool use.
Strong in non-human identity: OAuth, SSO, SCIM, service accounts, and secrets.
Writes and ships code, building the tooling instead of stopping at a recommendation.
Explains risk clearly to engineers and non-engineers, and can say yes with conditions.
Works independently, is comfortable in greenfield work, and is willing to join the on-call rotation.
Uses AI in everyday work and has informed judgment about where it is useful.
Nice to have
Experience building evaluations or adversarial tests for AI systems.
Experience with AI gateways, SSPM, CASB, or DLP tools.
Familiarity with the NIST AI Risk Management Framework or ISO 42001.
Our Values at Beacon Software
Humility: We acknowledge that the path to getting to the right answer involves being wrong along the way. We have strong beliefs which are weakly held. We actively seek new ideas and believe we can learn from anyone at any time.
Honesty: We are truth seeking in our approach to business problems. Business is a repeat game and we believe that human relationships generate alpha. We understand that trust is earned over a lifetime and can be lost in an instant.
Hunger: We play to win. We hold ourselves to high standards and will not be outworked. We take pride in having a deep sense of responsibility to ourselves, each other, our partners, and our customers. We believe to whom much is given much is expected.
Horizon: We seek to build a generational software company. This will take decades. We manage our expectations and those of our partners to take advantage of the 8th wonder of the world - compounding growth.
How We Use AI in Our Hiring Process: To ensure transparency, we want candidates to know that Beacon Software uses Artificial Intelligence and AI-enabled tools to assist with screening, reviewing, organizing and highlighting profiles and applications that match the key requirements for each role.
AI does not make hiring decisions: Every application is reviewed by a member of our team, and all decisions throughout the process are made by humans. We use AI to support efficiency and consistency, not to replace human judgment. We are committed to a fair, thoughtful, and equitable experience for every candidate.
How well do you match this job?
Free account needed to apply or save. It takes a minute, and we'll bring you right back to this job.