Senior Offensive AI Security Engineer II
S
SamsaraAI security
This role is open to candidates residing in the US except the San Francisco Bay Metro Area, NYC Metro Area, and Washington, D.C. Metro Area.Full-TimeSenior
SalaryAnnual Base Salary $157,675 — $238,500 USD
Apply NowOpens the employer's application page
Job Details
- Experience
- 8+ years of experience in application security, vulnerability management, threat modeling, offensive security, or a closely related discipline
- Required Skills
- AWSGoGitHub
Requirements
- Have 8+ years of experience in application security, vulnerability management, threat modeling, offensive security, or a closely related discipline.
- Demonstrate application-fix impact and influence across a large part of an organization.
- Have hands-on experience building AI or agentic workflows for security use cases.
- Have experience conducting technical security assessments across software and hardware or firmware environments.
- Have experience creating secure-code solutions with engineers using languages such as GoLang.
- Have experience developing AI and agentic solutions using GitHub and developing within AWS cloud.
- AI-specific attack techniques, such as prompt injection, jailbreaks, and model or agent abuse, are an ideal qualification.
- Experience with security controls for agentic AI, RAG systems, or LLM-integrated platforms is an ideal qualification.
- LLM red-teaming and LLM evaluation or benchmarking experience are ideal qualifications.
- Bug bounty platform experience, such as Bugcrowd, is an ideal qualification.
- Experience in federal or FedRAMP-style environments is an ideal qualification.
- A track record of driving organization-wide security strategy or presenting technical findings to senior or executive stakeholders is an ideal qualification.
- Relevant industry certifications such as OSCP, GIAC, CISSP, or AWS certifications are ideal qualifications.
Responsibilities
- Assess Samsara software, code, and firmware for resilience against AI-driven and adversarial attacks, and implement fixes.
- Translate general AI security findings into application security fixes, adapting software techniques for hardware and embedded firmware.
- Find AI-specific and traditional vulnerabilities, including injection and IDOR, using AI-driven offensive validation.
- Build and pressure-test AI-enabled security tools and workflows, then drive adoption across the security organization.
- Benchmark new frontier models against previous models for security tasks and define release criteria and adoption guardrails.
- Support AppSec vulnerability triage through an office-hours rotation and help run the bug bounty program.
- Partner with engineering, hardware, and leadership, and present findings to security and executive leadership.
- Help define and drive the medium- and long-term strategy for safe and effective AI adoption in security operations.
View Full Description & ApplyYou'll be redirected to the employer's site
