AI Red Team — Penetration Testing Expert
- Toronto, Ontario, Canada
- Remote
- Posted Oct 13, 2026
- 1 position
US$60–US$120 / hour
Opens LinkedIn
- Employment type
- Contract
- Posting language
- English
- Location requirements
- Country, Toronto, Ontario, Canada
Job summary
Conduct penetration tests and realistic attack simulations against AI-powered applications, APIs, infrastructure, and machine-learning pipelines, including testing for AI-specific vulnerabilities. Document findings with evidence, severity ratings, and actionable remediation guidance, while contributing insights to improve AI security testing methods.
Job details
About The Role What if your hacking skills could directly shape how safe and secure AI systems are for millions of users worldwide? We're looking for Penetration Testing Experts to join AI red team engagements — probing, attacking, and stress-testing AI-powered applications and infrastructure to identify vulnerabilities before bad actors do. This is a fully remote, flexible contract role where your offensive security expertise meets the cutting edge of artificial intelligence. You'll work on high-impact projects that directly improve the security posture of AI systems used at scale. Organization: Alignerr Type: Hourly Contract Location: Remote Commitment: 10–40 hours/week What You'll Do Conduct penetration tests against AI-powered applications, APIs, and infrastructure to uncover security vulnerabilities Identify and exploit weaknesses in AI/ML pipelines, including prompt injection, model manipulation, data poisoning vectors, and authentication flaws Perform web application, network, and API security assessments using industry-standard tools and methodologies Simulate real-world attack scenarios — from reconnaissance through exploitation and post-exploitation Document findings in clear, structured reports with severity ratings, evidence, and actionable remediation guidance Evaluate AI-specific attack surfaces including adversarial inputs, jailbreaks, and data exfiltration risks Stay current with emerging AI security threats and contribute insights to improve testing methodologies Work independently on task-based engagements on your own schedule Who You Are Experienced penetration tester with a strong understanding of offensive security principles and methodologies (OWASP, PTES, MITRE ATT&CK) Proficient with industry-standard tools such as Burp Suite, Metasploit, Nmap, Kali Linux, or equivalent Solid understanding of web application security, network security, and API security testing Able to think like an attacker — creative, persistent, and methodical in finding what others miss Strong written communication skills — you can translate complex technical findings into clear, actionable reports Self-motivated and reliable when working independently without direct supervision Comfortable working across diverse technology stacks and environments Nice to Have Relevant certifications such as OSCP, OSCE, CEH, GPEN, GXPN, or eWPT Experience with AI/ML security testing — adversarial machine learning, prompt injection, LLM red-teaming Background in red teaming, bug bounty programs, or CTF competitions Familiarity with cloud security (AWS, GCP, Azure) and container security Programming or scripting skills in Python, Bash, PowerShell, or similar Knowledge of secure development practices and DevSecOps workflows Experience conducting security assessments in compliance-driven environments (SOC 2, ISO 27001, etc.) Why Join Us Work on cutting-edge AI security projects alongside leading research labs Fully remote and flexible — work when and where it suits you Freelance autonomy with access to high-impact, intellectually challenging engagements Be at the forefront of AI security — a rapidly growing field with massive demand Sharpen your skills against novel AI-specific attack surfaces that few security professionals have encountered Contribute directly to making AI systems safer and more trustworthy for users worldwide Potential for ongoing work and contract extension as new projects launch
What you’ll do
Conduct penetration tests and realistic attack simulations against AI-powered applications, APIs, infrastructure, and machine-learning pipelines, including testing for AI-specific vulnerabilities. Document findings with evidence, severity ratings, and actionable remediation guidance, while contributing insights to improve AI security testing methods.
Requirements
Candidates should have penetration-testing experience, knowledge of offensive security methodologies such as OWASP, PTES, and MITRE ATT&CK, and proficiency with standard security tools. They should also understand web, network, and API security, communicate findings clearly, and work independently; AI/ML security experience and relevant certifications are preferred.
Benefits
- Fully Remote
- Flexible Schedule
- Freelance Autonomy
- High-Impact Projects
- Potential for Ongoing Work and Contract Extension
Listed skills
- Burp Suite · Preferred
- Metasploit · Preferred
- Nmap · Preferred
- Python · Preferred
Other relevant skills
Identified from the job description. Confirm important requirements above.
- Penetration Testing
- Offensive Security
- AI Security Testing
- Web Application Security
- Network Security
- API Security
- Red Teaming
- Vulnerability Assessment
- Prompt Injection Testing
- Adversarial Machine Learning
- Security Reporting
- Burp Suite
- Metasploit
- Nmap
- Kali Linux
- Python
Job areas
- Security & Safety
- Technology
- Software
- Engineering
Do this kind of work? Join the Jobs.ca expert list.
One short form. We email you when a paid AI-training project fits your field. Joining does not guarantee work.
Join the listMore jobs from Alignerr
Population Health Informaticist
- Remote
- Vancouver, British Columbia, Canada
- Posted Nov 16, 2026
Medical Science Liaison (MSL)
- Remote
- Toronto, Ontario, Canada
- Posted Nov 16, 2026
Medical Science Liaison (MSL)
- Remote
- Edmonton, Alberta, Canada
- Posted Nov 16, 2026
Health Informatics Analyst
- Remote
- Edmonton, Alberta, Canada
- Posted Nov 16, 2026
