Sr. AI Security Engineer

Backblaze; United States; Remote; USD 150,000 - 190,000; Full time

Benefits offered by this job

Remote LATAM role

Family healthcare

401(k)

RSU grants

ESPP

Flexible vacation

Parental leave

Childcare support

Commuter benefits

L&D program

Job summary

Backblaze is seeking a senior security engineer to design and deploy guardrails for internal AI usage across a large-scale cloud platform. You will implement runtime enforcement, identity controls, and detection capabilities to safeguard developers using AI-assisted coding tools.

Applicants should have 7+ years in security or backend systems, strong Python, and familiarity with agentic AI workflows, OWASP guidance, and observability tooling. Remote LATAM role with strong security impact.

Qualifications

• 7+ years of experience in security engineering or backend systems.
• Strong programming in Python; Go, Java, or TypeScript a plus.
• Practical familiarity with agentic AI systems or tool-integrated LLM workflows, and OWASP guidance for AI and agent risks.
• Experience with non-human identity, zero trust, secrets management, credential scoping, and observability tooling such as OpenTelemetry or ELK.
• Hands-on experience applying OWASP Agentic AI or LLM risk guidance, NIST AI RMF concepts, and CSA guidance on workload and machine identity in real systems.
• Experience using AI-assisted development tools such as Claude Code, Codex, or Cursor in real workflows, including their associated risks and safeguards.

Responsibilities

• Architect and implement guardrails for tool-using AI systems, including tool allowlists, context and memory isolation, and step-level validation of agent actions aligned to OWASP Agentic AI guidance.
• Build runtime enforcement mechanisms such as interceptors, proxies, middleware, policy decision layers, rate limits, execution bounds, and kill-switches that govern AI behavior at execution time.
• Design identity and access systems for agents and automation, including short-lived credentials, scoped permissions, clear separation between human and non-human identities, and full audit attribution.
• Implement logging and tracing for prompts, tool usage, and decision flows, and build detection capabilities using behavioral baselining and anomaly detection.
• Perform agentic system threat modeling using the MAESTRO framework, mapping capabilities, trust boundaries, and attack paths, and translate findings into safeguards and detection logic.
• Protect developers using AI tools by preventing sensitive data exposure, validating AI-generated code and actions, and enabling safe usage of AI-assisted development tooling.

Skills

Security engineering

Backend systems

Python

Go/Java/TypeScript

Agentic AI

Observability tooling

OWASP AI guidance

NIST AI RMF

CSA guidance

AI tools usage

Tools

OpenTelemetry

ELK

Job description

Role overview

A senior, hands-on security engineering role focused on safeguarding internal AI usage, especially agentic and tool-using systems, within a large-scale cloud environment. The position designs and builds runtime enforcement, identity controls, and detection capabilities rather than only defining policy, and protects developers using AI-assisted coding tools. It suits a practitioner who has shipped security controls in production and is comfortable working across AI, identity, and observability domains.

Responsibilities

• Architect and implement guardrails for tool-using AI systems, including tool allowlists, context and memory isolation, and step-level validation of agent actions aligned to OWASP Agentic AI guidance.
• Build runtime enforcement mechanisms such as interceptors, proxies, middleware, policy decision layers, rate limits, execution bounds, and kill-switches that govern AI behavior at execution time.
• Design identity and access systems for agents and automation, including short-lived credentials, scoped permissions, clear separation between human and non-human identities, and full audit attribution.
• Implement logging and tracing for prompts, tool usage, and decision flows, and build detection capabilities using behavioral baselining and anomaly detection.
• Perform agentic system threat modeling using the MAESTRO framework, mapping capabilities, trust boundaries, and attack paths, and translate findings into safeguards and detection logic.
• Protect developers using AI tools by preventing sensitive data exposure, validating AI-generated code and actions, and enabling safe usage of AI-assisted development tooling.

Requirements

• 7+ years of experience in security engineering or backend systems, with proven experience designing and deploying security controls in production.
• Strong programming skills in Python; Go, Java, or TypeScript a plus.
• Practical familiarity with agentic AI systems or tool-integrated LLM workflows, and OWASP guidance for AI and agent risks.
• Experience with non- human identity, zero trust, secrets management, credential scoping, and observability tooling such as OpenTelemetry or ELK.
• Hands-on experience applying OWASP Agentic AI or LLM risk guidance, NIST AI RMF concepts, and CSA guidance on workload and machine identity in real systems.
• Experience using AI-assisted development tools such as Claude Code, Codex, or Cursor in real workflows, including their associated risks and safeguards.

Nice to have

• Background securing internal AI platforms or developer-facing AI tools.
• Experience in detection engineering, threat hunting, or adversarial testing.Familiarity with agent frameworks such as LangChain or LlamaIndex.
• Experience mentoring engineers and guiding secure design.

Benefits and work setup

• Remote role based in the LATAM region, focused on internal AI security work for a large-scale cloud platform.
• Family healthcare including dental and vision, 401(k), RSU grants, ESPP, flexible vacation, parental leave, childcare and fertility support, commuter benefits, and a learning and development program.
• Company laptop plus a workstation personalization stipend and a culture that supports work-life balance.