Overview

AI Safety Analyst Jobs in South Africa at Alignerr

Title: AI Safety Analyst

Company: Alignerr

Location: South Africa

About The Role

What if your curiosity and critical thinking could make AI safer for millions of people? We're looking for AI Safety Analysts to put cutting-edge AI systems under pressure — probing, testing, and uncovering issues before they reach the real world.

This is more than a reviewing job. You'll be on the front lines of responsible AI development, working with leading research labs to ensure AI models behave safely, appropriately, and reliably across a wide range of scenarios. No AI or cybersecurity background required — just a sharp, questioning mind and clear communication skills.

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

What You'll Do

  • Put AI systems through rigorous testing using challenging, adversarial, and edge-case inputs
  • Identify unsafe, harmful, biased, or inappropriate AI outputs across a variety of scenarios
  • Document safety issues clearly and precisely, with detailed examples and explanations
  • Rate AI responses against safety and helpfulness criteria using structured evaluation frameworks
  • Follow red-teaming guides and structured testing protocols to systematically surface vulnerabilities
  • Work independently and asynchronously on your own schedule

Who You Are

  • A natural critical thinker who enjoys poking at things to see how they break
  • Comfortable exploring edge cases, unusual scenarios, and unconventional thinking
  • Strong written communicator — you can describe a problem clearly and precisely
  • Genuinely interested in AI safety, ethics, and responsible technology
  • Detail-oriented and consistent in your approach
  • No cybersecurity, AI, or technical background required

Nice to Have

  • Experience in journalism, research, ethics, or quality assurance
  • Familiarity with AI tools or chatbots as a regular user
  • Background in psychology, philosophy, or social sciences — useful for understanding human-AI interaction
  • Prior experience with structured evaluation or content review work

Why Join Us

  • Work on meaningful AI safety projects alongside top research labs shaping the future of AI
  • Fully remote and flexible — work on your own schedule, from anywhere
  • Freelance autonomy with the structure of impactful, task-based assignments
  • Contribute to work that genuinely matters — your findings help keep AI safe for real users
  • Variety in every project — no two testing sessions are the same
  • Potential for ongoing work and contract extension as new AI projects launch
Upload your CV/resume or any other relevant file. Max. file size: 800 MB.