Sr. AI Security Engineer

Overview

Design and implement safeguards for internal AI usage, with a focus on agentic systems, developer protection, and runtime security. This is a hands-on role for a practitioner who has built and deployed security controls, not just defined policy.

What you'll do

• Architect and implement guardrails for tool-using AI systems, including tool access controls and allowlists, context and memory isolation, and step-level validation of agent actions.
• Apply mitigations aligned to the OWASP Agentic AI Top 10 (e.g., prompt injection, unsafe tool use, data leakage, excessive autonomy).
• Build runtime enforcement mechanisms: interceptors, proxies, or middleware for tool/API calls; policy decision and enforcement layers; rate limits, execution bounds, and kill-switches.
• Prevent unsafe or unauthorized actions initiated by AI systems.
• Design and implement identity and access controls for agents and automation, including short-lived credentials, scoped permissions, clear separation between human and non-human access, and strong binding of identity to task context and execution.
• Ensure all AI actions are attributable and auditable.
• Implement logging and tracing for AI activity, including prompts, tool usage, and decision flows.
• Build detection capabilities using behavioral baselining and anomaly detection techniques to identify abnormal tool usage, suspicious prompt patterns, and unexpected data access.
• Perform agentic system threat modeling using MAESTRO, mapping agent capabilities, trust boundaries, and attack paths, modeling misuse and adversarial scenarios, and translating findings into practical safeguards and detection logic.
• Protect developers using AI tools by preventing sensitive data exposure, validating AI-generated code and actions, and constraining unsafe automation.
• Enable safe usage of AI-assisted development tools (e.g., Claude Code, Codex, Cursor) with security validation layers and controlled prompting and output handling patterns.

What you'll need

• 7+ years in security engineering or backend systems.
• Proven experience designing and deploying security controls, such as runtime enforcement layers (proxies, middleware, policy engines) and identity and access systems, especially for non-human entities.
• Strong programming skills in Python.
• Experience using AI-assisted development tools such as Claude Code in real workflows, including understanding associated security risks and safeguards.
• Experience with logging, monitoring, and detection systems.
• Experience building or securing API/service interactions.
• Practical familiarity with agentic AI systems or tool-integrated LLM workflows.
• Practical familiarity with OWASP guidance for AI/agent risks.
• Experience applying OWASP Agentic AI / LLM risk guidance, NIST AI RMF concepts in real systems, and CSA guidance on workload and machine identity.
• Strong understanding of Zero Trust for non-human identities, secrets management and credential scoping, and observability tooling (e.g., OpenTelemetry, ELK).

Nice to have

• Go, Java, or TypeScript.
• Experience securing internal AI platforms or developer-facing AI tools.
• Background in detection engineering, threat hunting, or adversarial testing.
• Familiarity with agent frameworks (e.g., LangChain, LlamaIndex).
• Experience mentoring engineers and guiding secure design.

Details

• Location: Remote in Colombia, Costa Rica, or Mexico.