AI Safety & Red Teaming Specialist

14 hours, 37 minutes ago
Contract
Junior
Artificial Intelligence and Machine Learning
Weekday

Weekday

Weekday helps companies hire engineers who are vouched by other software engineers, enabling passive income for engineers. They offer services like drafting outreach messages, shortlisting candidates, and conducting reference checks. Backed by Y Combin...

Construction & Engineering
11-50
Founded 2020

Description

  • Design and implement advanced evaluation methodologies for AI system safety, including ethical jailbreak testing, prompt injection detection, LLM red teaming, and tool-use abuse scenarios.
  • Develop cross-domain adversarial testing strategies to uncover complex, multi-turn attack patterns and model vulnerabilities.
  • Build, maintain, and enhance regression test suites to continuously assess jailbreak susceptibility and prompt injection risks.
  • Create comprehensive evaluation frameworks that simulate real-world adversarial threats to improve AI robustness and reliability.
  • Collaborate with technical teams to translate security findings into actionable recommendations for AI safety improvements.
  • Document testing methodologies, findings, and best practices in clear technical reports and presentations for technical and non-technical stakeholders.

Requirements

  • 2+ years of experience in AI Safety, Adversarial Machine Learning, LLM Red Teaming, AI Security, or a related field.
  • Hands-on experience researching, testing, or identifying vulnerabilities involving prompt injection, ethical jailbreaks, adversarial attacks, or tool-use exploitation.
  • Strong understanding of modern LLM architectures, prompt engineering, and AI safety evaluation methodologies.
  • Experience developing structured security assessments, regression testing frameworks, and adversarial evaluation strategies.
  • Excellent analytical, documentation, and communication skills with the ability to explain complex technical findings clearly.
  • Ability to collaborate effectively within cross-functional technical teams.
  • Master's or PhD in Computer Science, Cybersecurity, Machine Learning, Artificial Intelligence, or a related discipline is preferred.
  • Contributions to AI security research, open-source AI safety tools, conference presentations, or published research are preferred.
  • Experience with AI model evaluation frameworks, prompt engineering techniques, and AI security assessment tools is preferred.
  • Background in multidisciplinary AI safety, cybersecurity, or adversarial machine learning projects is preferred.
  • AI Safety.
  • LLM Red Teaming.
  • Prompt Injection.
  • Adversarial Machine Learning.
  • Ethical Jailbreaking.
  • AI Security.
  • Prompt Engineering.
  • AI Evaluation Frameworks.

Benefits

  • $50 - $90/hour pay.
  • Remote work location.
  • Contractor role.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Senior AI Business Analyst (6 months FTC) (m/f/d)

Booksy 251-1K Diversified Consumer Services

Booksy is seeking a Senior AI Business Analyst to help lead its global AI transformation program by mapping current operations, identifying high-value AI opportunities, and turning them into scalable workflows.

Generative AI LLM
14 hours, 22 minutes ago

Customer Support Specialist - Freelance AI Trainer

Mindrift.ai: Be the “I” in AI Internet Software & Services

Mindrift is seeking English-proficient project-based contributors to test, evaluate, and improve AI systems through customer service and financial-services scenario work.

14 hours, 22 minutes ago

Earn $25 for Up to 20 Minutes Voice Recording Only - Standard American English

Volga Partners 51-250 Internet Software & Services

Volga Partners is recruiting remote participants for a one-time English voice biometrics research study that helps build AI speech technology.

Android iOS macOS Monday.com
14 hours, 22 minutes ago

Customer Support Specialist - Freelance AI Trainer

Mindrift.ai: Be the “I” in AI Internet Software & Services

Mindrift is seeking project-based contributors to test, evaluate, and improve AI systems for customer-service scenarios in banking and financial services.

14 hours, 22 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers