Cloud Security Analyst (AI Training) About the Role We're partnering with leading AI research labs to build smarter, safer AI systems — and we need practitioners who know how cloud environments actually fail in the real world. This isn't theoretical work.
Offensive Security Analyst (Structured / Non-Exploit)
Remote (Global)
$40 – $60/hr
July 14, 2026
Job description
Offensive Security Analyst (Structured / Non-Exploit) — AI Training
About the Role
What if your offensive security instincts could directly shape how AI understands and reasons about real-world threats? We're looking for experienced security professionals to analyze adversarial attack paths, model threat behavior, and help build the next generation of AI systems that understand cybersecurity at a deep, practical level.
This is a fully remote, flexible contract role — no exploit development required. You'll bring your red team mindset to structured adversarial reasoning: mapping how attacks unfold, where defenses break down, and how risk spreads across modern environments.
- Organization: Alignerr
- Type: Hourly Contract
- Location: Remote
- Commitment: 10–40 hours/week
What You'll Do
- Analyze real-world attack paths, kill chains, and adversary strategies across a range of modern environments
- Classify weaknesses, misconfigurations, and defensive gaps in realistic system scenarios
- Review and evaluate red team-style scenarios and intrusion narratives for technical accuracy and depth
- Generate, label, and validate adversarial reasoning data used to train and evaluate frontier AI systems
- Articulate how attacks unfold, what impact they create, and what tradeoffs defenders face — in clear, structured language
- Work independently and asynchronously on task-based assignments at your own pace
Who You Are
- 2+ years of hands-on experience in pentesting, red teaming, or a blue-team role with deep attack knowledge
- You understand how real attacks actually unfold in production environments — not just in theory
- Able to clearly explain attack chains, attacker objectives, and defensive implications to a technical audience
- Naturally systematic and detail-oriented — you think in adversary mindsets and can map threat behavior end-to-end
- Strong written communicator who can translate complex technical concepts into structured, accessible analysis
- Comfortable working independently without close supervision
Nice to Have
- Experience with MITRE ATT&CK, threat modeling frameworks, or structured kill-chain analysis
- Background in threat intelligence, incident response, or security architecture
- Familiarity with cloud environments, Active Directory, or network security concepts
- Prior work annotating, labeling, or evaluating technical content
- Interest in AI safety, AI security, or how AI systems reason about complex domains
Why Join Us
- Work directly on frontier AI systems alongside leading AI research labs
- Fully remote and flexible — structure your work around your schedule
- Freelance autonomy with meaningful, intellectually engaging work
- Apply your offensive security expertise to a genuinely novel and high-impact domain
- Potential for ongoing work and contract extension as new projects launch
Compensation by region
Pay varies by where you're based. Each region below is open to applicants in that country only.
Available in 2 regions: pick your country on click.
Data Security & DLP Analyst (AI Training) About the Role We're looking for experienced data security professionals to help train and evaluate cutting-edge AI systems.
Vulnerability Management Analyst (AI Training) About the Role We're looking for experienced vulnerability management and security operations professionals to help evaluate and improve cutting-edge AI systems.
Identity & Access Management (IAM) Analyst (AI Training) About the Role Identity sits at the core of most modern enterprise security failures — and we need experts who truly understand why.