Project details
Recommended projects
Freelance Cybersecurity Consultant for AI Red Teaming
AI Evaluation Consultant (m/w/d)
Freelance Automotive Engineer (with Python) - Quality Assurance / AI Trainer
Vibe Coding Web Scraping Expert (m/f/d)
Evaluation Scenario Writer (m/w/d)
AI Consultants - Data Science (m/w/d)
Data Engineer (m/f/d)
Cyber Security Consultant – Product Security & Regulatory Compliance (f/m/d)
ISO 20121 Auditor (w/m/d)
Auditor – FSC® and PEFC Chain of Custody (m/f/d)
Social Compliance Auditor (m/f/d)
Construction Manager according to LBO - Civil and MEP (m/f/d)
Senior Regulatory Compliance Expert (FDA Inspection Preparation) (m/f/d)
Commissioning & Qualification (C&Q) Engineer (m/f/d)
Quality Compliance Auditor (GCP/GCLP/GVP) (M/W/D)
Tax Strategy Consulting
Senior Project Manager Customer Interaction
Senior Cloud Developer TypeScript (m/f/d)
HSE Specialist – Body in White (M/W/D)
HSE Specialist – Cell Manufacturing
ERP Transformation Manager (m/f/d)
HSE Specialist – Facilities (M/W/D)
Java IT Architect (m/f/d)
Freelance Product Owner for Point Of Sale App
IT Project Manager ISO 27.001 - Gap Closure (m/f/d)
Interim Staff Product Manager (m/w/d)
Safety and Health Protection Coordinator (SiGeKo) and Safety Specialist (SiFa) (m/f/d)
Cyber Risk Consulting (Senior Level)
Adobe Experience Cloud Consultant (m/f/d)
Management Consultant (Senior Level) (m/w/d)
Frontend developer to HR platform with Angular experience
Freelance Cybersecurity Consultant for AI Red Teaming
Project info
- Period09.03.2026 - 29.04.2026
- Capacityfrom 5%
- Daily rate120 - 360€
- Language
- English(Advanced)
- English
- Remotefrom 95%
Description
We are looking for cybersecurity consultants to help train an AI model (Large Language Model - LLM) for an AI lab.
You will help the AI understand the world. As a consultant, you might be invited to join online projects to train the model in your area of expertise.
This flexible role is open to experts seeking part-time work (at least a few hours per week) or those looking for full-time opportunities:
- Evaluate and red-team AI models, agents, and machine learning systems for vulnerabilities and safety risks.
- Create offline, reproducible and auto-evaluable test cases to assess the safety and capabilities of AI agents.
- Develop and implement automation scripts, custom tools, environments, and test harnesses.
- Lead or contribute to security research initiatives, especially in AI safety, by designing and executing realistic, challenging attack scenarios for the model.
- Advise on cybersecurity best practices and policy implications.
Requirements
- Proficient in scripting and automation using Python, Bash, or PowerShell.
- Experienced with containerization and CI/CD security tools, especially Docker.
- Hands-on experience with penetration testing across web, API, network, and infrastructure environments.
- Knowledge of vulnerabilities in current AI models, including prompt injections, and familiarity with the OWASP Top 10 for Large Language Models (LLMs).
- Familiar with AI red-teaming frameworks such as garak or PyRIT.
- Experience in AI/ML security, evaluation, and red teaming, particularly with LLMs, AI agents, and RAG pipelines.
- Proficient in offensive exploitation and exploit development.
- Skilled in reverse engineering using tools like Ghidra or equivalents.
- Expertise in network and application security, including web application security.
- Knowledge of operating system security concepts such as Linux privilege escalation and Windows internals.
- Familiar with secure coding practices for full-stack development.
Application Process:
- If selected, you will be invited to an interview by Mindrift.