Careers / Career tracks

Career track

AI Safety and Evaluation career track

Test how models fail and measure it: safety bypasses, evaluation and clear write-ups. Follow the four stages below: learn, practise, prove, apply.

  • 5 skills
  • 1 open role
  • Free

What counts

  1. Skills from labs60 points
  2. Reports and proof25 points
  3. Learning15 points

Sign in to see your own score.

Skills this track builds

Each skill fills as you solve its labs.

  • Jailbreaks and safety bypass0%
  • Prompt injection0%
  • Model and ML attacks0%
  • Prompt and data leakage0%
  • Report writing0%

1Learn

Start with the material that explains the ideas before you attack anything.

Courses

Lessons on hunting with AI

Tutorials

2Practise

Labs grouped by skill, easiest first. They run in the browser.

Jailbreaks and safety bypass 0 of 8 solved

All 8 labs for this skill

Prompt injection 0 of 14 solved

All 14 labs for this skill

Model and ML attacks 0 of 5 solved

All 5 labs for this skill

Prompt and data leakage 0 of 8 solved

All 8 labs for this skill

3Prove

Solving labs shows practice. These show an employer you can do the job.

4Apply

Open AI Safety and Evaluation roles right now.

Mid-level interview questionsBuild your application kitAll open roles