Offensive Security Professional - AI Systems Training and Evaluation

Alignerr United Kingdom
Remote
Apply
AI Summary

Join Alignerr as an offensive security professional to apply your adversarial mindset to training and evaluating frontier AI models. Analyze realistic attack paths, identify weaknesses, and generate adversarial reasoning data. Work independently and asynchronously on your own schedule.

Key Highlights
Analyze realistic attack paths and adversary strategies
Generate and label adversarial reasoning data
Work independently and asynchronously
Key Responsibilities
Analyze realistic attack paths
Identify weaknesses
Generate and label adversarial reasoning data
Work independently and asynchronously
Technical Skills Required
Pentesting Red teaming Blue-team role MITRE ATT&CK Cloud attack surfaces (AWS, Azure, GCP)
Benefits & Perks
Fully remote and flexible work
Freelance autonomy with structured task-based work
Potential for ongoing work and contract extension
Nice to Have
Threat modeling
Purple teaming
Adversary simulation exercises
Certifications (OSCP, GPEN, GWAPT)

Job Description


About The Role

What if your knowledge of how attacks unfold — how adversaries move, where defenses crack, and how risk cascades across modern infrastructure — could directly shape the AI systems that millions of people will rely on for security guidance?

We're looking for offensive security professionals to apply their adversarial mindset to a new kind of challenge: training and evaluating frontier AI models. This role is about structured threat reasoning, not exploit development. If you can think like an attacker and explain it clearly, you're exactly who we need.

This is a fully remote, flexible contract role — work on your own schedule, on your own terms.

  • Organization: Alignerr
  • Type: Hourly Contract
  • Location: Remote
  • Commitment: 10–40 hours/week

What You'll Do

  • Analyze realistic attack paths, kill chains, and adversary strategies across modern production environments
  • Identify weaknesses, misconfigurations, and defensive gaps in system and network scenarios
  • Review red-team-style intrusion narratives and evaluate their technical accuracy and completeness
  • Generate, label, and validate adversarial reasoning data used to train and evaluate AI systems
  • Articulate attack chains, blast radius, and risk tradeoffs in clear, structured written form
  • Work independently and asynchronously — on your own schedule

Who You Are

  • 2+ years of hands-on experience in pentesting, red teaming, or a blue-team role with deep attack-side knowledge
  • Solid understanding of how real attacks unfold across endpoints, networks, cloud environments, and identity systems
  • Able to map adversary behavior to frameworks like MITRE ATT&CK and explain the "why" behind attack decisions
  • Clear, precise communicator — you can explain complex attack chains to both technical and non-technical audiences
  • Detail-oriented and consistent when working through structured evaluation tasks

Nice to Have

  • Experience with threat modeling, purple teaming, or adversary simulation exercises
  • Familiarity with cloud attack surfaces (AWS, Azure, GCP)
  • Background in incident response or threat intelligence
  • Certifications such as OSCP, GPEN, GWAPT, or equivalent real-world experience
  • Prior exposure to AI tools or data labeling workflows

Why Join Us

  • Work directly on frontier AI systems alongside leading AI research labs
  • Fully remote and flexible — work when and where it suits you
  • Freelance autonomy with the structure of meaningful, task-based work
  • Apply your offensive security expertise in a novel, high-impact domain
  • Potential for ongoing work and contract extension as new projects launch

Similar Jobs

Explore other opportunities that match your interests

Security Operations Incident Response Specialist

Cyber Security
12h ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

monzo bank

United Kingdom
Visa Sponsorship Relocation Remote
Job Type Part-time
Experience Level Associate

weekday ai (yc w21)

United Kingdom

Security Training Lab Developer

Cyber Security
6d ago
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Entry level

SecureFlag

United Kingdom

Subscribe our newsletter

New Things Will Always Update Regularly