Senior AI Security Engineer — Agentic & Runtime Safeguards

Backblaze External Website; Colombia; Remote; COP 140,000,000 - 210,000,000; Full time

Job summary

Backblaze is seeking a Senior AI Security Engineer to 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 requiring building and deploying security controls, enforcement layers, identity controls, and detection capabilities to enable safe AI-driven development across teams.

You will translate threat modeling results into practical safeguards and work with AI tooling like Claude Code, Codex,

Qualifications

• 7+ years in security engineering or backend systems.
• Proven experience designing and deploying security controls.
• Experience with logging, monitoring, and detection systems.
• Familiarity with agentic AI systems or tool-integrated LLM workflows.
• Knowledge of OWASP Agentic AI / LLM risks, NIST AI RMF concepts, and CSA guidance.

Responsibilities

• Architect and implement guardrails for tool-using AI systems; include access controls, context isolation, and step-level validation.
• Build enforcement mechanisms for AI execution-time governance (interceptors, proxies, policy layers, rate limits, kill-switches).
• Design and implement identity and access controls for agents/non-human identities with short-lived credentials and task-context binding.
• Implement logging, tracing, and detection for AI activity (prompts, tool usage, decision flows).
• Perform MAESTRO-based agentic threat modeling and translate findings into safeguards and detection logic.

Skills

Security engineering

Backend systems

Designing security controls

Logging & monitoring

Threat modeling

Agentic AI systems

LLM workflows

Zero Trust for non-human identities

Tools

Claude Code

Codex

Cursor

OpenTelemetry

ELK

Job description

Backblaze is seeking a Senior AI Security Engineer to 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 requiring building and deploying security controls, enforcement layers, identity controls, and detection capabilities to enable safe AI-driven development across teams.

You will translate threat modeling results into practical safeguards and work with AI tooling like Claude Code, Codex,