Senior Security Engineer, AI Security

Beacon Holdings•New York, NY

About The Position

Beacon is seeking a Senior Security Engineer to own the safe use of AI at Beacon and across its portfolio companies. The role designs and operates security controls, hardens the systems that AI tools and agents connect to, and partners with engineering on identity, authorization, and network protections for AI agents and other non-human workloads. The engineer builds and ships security tooling, threat-models and tests AI systems, establishes monitoring and response practices, and helps teams adopt AI tools through clear approval patterns. The role also adds AI inventory and security standards to the baseline for each acquisition.

Requirements

  • About 5 to 7 years of experience 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 knowledge of non-human identity, including OAuth, SSO, SCIM, service accounts, and secrets.
  • Ability to write and ship code and build tooling, not just make recommendations.
  • Ability to explain risk clearly to engineers and non-engineers and provide approvals with conditions.
  • Ability to work independently in greenfield environments.
  • Willingness to join the on-call rotation.
  • Uses AI in everyday work and has informed judgment about where it is useful.

Nice To Haves

  • 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.

Responsibilities

  • Assign every agent an owner and scoped credentials, enforce least privilege and appropriate approvals, and track agents from creation through offboarding like users.
  • Own security requirements for AI integrations, including MCP connections and OAuth grants, as well as memory and retrieval; establish tenant defaults and approved connectors.
  • Maintain a live inventory of AI tools and agents, including AI features vendors enable within existing tools.
  • Set limits on tool calls, network access, data egress, and resource use.
  • Threat-model and adversarially test the internal AI platform and agents for prompt injection, data disclosure, unsafe tool use, and unauthorized actions.
  • Convert testing findings into regression tests and release gates.
  • Define required AI-system logging and build detections for risky grants and sensitive data entering AI tools.
  • Lead the AI side of security incidents and participate in the on-call rotation.
  • Review new AI tools efficiently, provide conditional approvals, and maintain approved patterns and a pre-cleared list to minimize routine reviews.
  • Add an AI inventory and related security standards to the security baseline for each acquisition.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service