AI Security Adversary Analyst — Remote Contract

Alignerr Corp.; Manchester; Remote; GBP 62,000 - 104,000; Full time

Benefits offered by this job

Fully remote

Job summary

Alignerr is seeking an experienced offensive security professional to train and evaluate frontier AI models. This fully remote, flexible hourly contract role emphasizes structured threat reasoning over exploit development.

You will work on your own schedule, applying adversarial mindset to real-world AI security challenges. Ideal candidates have 2+ years in pentesting/red teaming or blue-team roles, with strong threat modeling and MITRE ATT&CK knowledge.

Qualifications

• 2+ years hands-on security testing or red-team experience.
• Understanding of how attacks unfold across endpoints, networks and cloud.
• Ability to map attacker behavior to MITRE ATT&CK and explain decisions.
• Able to explain attack chains clearly to technical and non-technical audiences.
• Detail-oriented and consistent in structured evaluation tasks.

Responsibilities

• Analyze attack paths, kill chains, and adversary strategies across environments.
• Identify weaknesses and defensive gaps in system and network configurations.
• Review red-team narratives and assess technical accuracy and completeness.
• Generate, label, and validate adversarial reasoning data for AI training.
• Articulate attack chains, blast radius, and riskTradeoffs in clear written form.
• Work independently and asynchronously on your schedule.

Skills

Pentesting

Red teaming

Blue‑team knowledge

MITRE ATT&CK

Clear communicator

Job description

Alignerr is seeking an experienced offensive security professional to train and evaluate frontier AI models. This fully remote, flexible hourly contract role emphasizes structured threat reasoning over exploit development.

You will work on your own schedule, applying adversarial mindset to real-world AI security challenges. Ideal candidates have 2+ years in pentesting/red teaming or blue-team roles, with strong threat modeling and MITRE ATT&CK knowledge.