Sr Offensive AI Security Engineer II

About the Role

Samsara is hiring an engineer at the intersection of security engineering and applied AI to serve as the most AI-forward technologist on our Application Security team. You will use frontier AI models to identify vulnerabilities across cloud, software, and firmware environments, evaluate new models for security use, and develop guardrails for safe AI adoption. This role reports directly into the AppSec team.

*Note: This position is open to US candidates residing outside of the SF Bay Metro Area, NYC Metro Area, and Washington, D.C. Metro Area.*

Key Responsibilities

• Deliver accurate, consistent security assessments of software, code, and firmware against AI-driven/adversarial attacks, and implement fixes.
• Translate general AI security findings into Samsara-specific fixes across software, hardware, and embedded firmware layers.
• Discover both AI-specific and traditional vulnerabilities (e.g., injection, IDOR) using AI-driven offensive validation.
• Build, pressure-test, and drive adoption of novel AI-enabled security tooling and workflows across the broader security organization.
• Benchmark frontier models for security tasks and establish release criteria and guardrails.
• Support AppSec vulnerability triage through an office-hours rotation and assist with the bug bounty program.
• Partner cross-functionally with engineering and hardware teams, presenting findings to security and executive leadership.
• Help define medium- and long-term security strategy for safe AI integration.
• Hands-on use of frontier AI/LLM tools for offensive validation (red-teaming) and defensive tooling.

Qualifications

Minimum Requirements

• 8+ years of experience in application security, vulnerability management, threat modeling, offensive security, or a closely related discipline.
• Hands-on experience building AI or agentic workflows for security use cases.
• Experience conducting technical security assessments (offensive security or validation exercises) across software and hardware/firmware environments.
• Experience creating solutions for secure code with engineers in languages such as Go.
• Experience developing AI and agentic solutions using GitHub and AWS.
• Experience integrating, securing, or red-teaming AI-enabled systems (LLMs, agentic workflows, prompt injection/adversarial testing).

Preferred Qualifications

• Experience with AI-specific attack techniques (prompt injection, jailbreaks, model/agent abuse).
• Experience building or validating security controls for agentic AI, RAG systems, or LLM-integrated platforms.
• Experience red-teaming and benchmarking/evaluating LLMs.
• Bug bounty platform experience (e.g., Bugcrowd).
• Experience in federal or FedRAMP-style environments.
• Track record of driving security strategy and presenting technical findings to senior/executive stakeholders.
• Relevant industry certifications (OSCP, CISSP, GIAC) or AWS certifications.