Sr. AI Security Engineer

3 months, 4 weeks ago
Senior
Artificial Intelligence and Machine Learning
Backblaze

Backblaze

Backblaze is a pioneer in robust, scalable low-cost cloud backup and storage services, offering enterprise hot storage, low-cost backup and archive solutions. With the easiest way to back up all files, Backblaze provides unlimited, unthrottled, and unc...

IT Services
251-1K
Founded 2007

Description

  • Architect and implement guardrails for tool-using AI systems, including tool access controls, allowlists, context isolation, and step-level validation.
  • Apply mitigations aligned to the OWASP Agentic AI Top 10, including prompt injection, unsafe tool use, data leakage, and excessive autonomy.
  • Build runtime enforcement mechanisms such as interceptors, proxies, middleware, policy layers, rate limits, execution bounds, and kill-switches.
  • Design identity and access controls for agents and automation, including short-lived credentials, scoped permissions, and human versus non-human access separation.
  • Implement logging, tracing, behavioral baselining, anomaly detection, and alerting for AI activity and suspicious behavior.
  • Perform agentic system threat modeling using MAESTRO 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 constraining unsafe automation.
  • Enable safe usage of AI-assisted development tools such as Claude Code, Codex, and Cursor through security validation layers and controlled prompting patterns.

Requirements

  • 7+ years of experience in security engineering or backend systems.
  • Proven experience designing and deploying security controls, including runtime enforcement layers and identity/access systems for non-human entities.
  • Strong programming skills; Python is preferred, with Go, Java, or TypeScript considered a plus.
  • Experience using AI-assisted development tools such as Claude Code in real workflows, including understanding related security risks and safeguards.
  • Experience with logging, monitoring, and detection systems.
  • Experience building or securing API and service interactions.
  • Practical familiarity with agentic AI systems or tool-integrated LLM workflows.
  • Practical familiarity with OWASP guidance for AI and agent risks.
  • Experience applying OWASP Agentic AI or LLM risk guidance, NIST AI RMF concepts, and CSA guidance on workload and machine identity.
  • Strong understanding of Zero Trust for non-human identities, secrets management, credential scoping, and observability tooling such as OpenTelemetry or ELK.
  • Preferred experience securing internal AI platforms or developer-facing AI tools.
  • Preferred background in detection engineering, threat hunting, or adversarial testing.
  • Preferred familiarity with agent frameworks such as LangChain or LlamaIndex.
  • Preferred experience mentoring engineers and guiding secure design.

Benefits

  • Backblaze offers the opportunity to join a public company with significant scale and growth.
  • The company supports learning, development, and career growth.
  • Backblaze has a culture that encourages applicants who do not meet every requirement to still apply.
  • The company values diversity, equity, and inclusion as core principles.
  • Backblaze is committed to fostering belonging across a wide range of backgrounds and identities.
  • Backblaze is proud to be an Equal Opportunity Employer.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

IT Security & Compliance Lead (Amsterdam, NLD)

B Lab 51-250 Diversified Consumer Services

B Lab is seeking a full-time IT Security & Compliance Lead in Amsterdam to establish consistent security governance, compliance, and risk management across its consolidating global network.

Cybersecurity Penetration Testing Salesforce
2 hours, 37 minutes ago

Insurance Expert - AI Training & Evaluation

Weekday 11-50 Construction & Engineering

Weekday is seeking experienced insurance professionals for a remote, project-based role creating and evaluating tasks used to train and assess advanced AI models.

2 hours, 37 minutes ago

IT Security & Compliance Lead (São Paulo, BR)

B Lab 51-250 Diversified Consumer Services

B Lab is seeking an IT Security & Compliance Lead in São Paulo to establish consistent security governance, compliance, risk management, and incident-response practices across its consolidating global nonprofit network.

Cybersecurity Penetration Testing Salesforce
2 hours, 37 minutes ago

Legal Expert - AI Training & Evaluation

Weekday 11-50 Construction & Engineering

Weekday is seeking practising lawyers or legal professionals for a remote, project-based role creating and evaluating legal tasks for advanced AI models as part of its AI training and evaluation project.

2 hours, 37 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers