Profile cover
J

AI Prompt Exfiltration Detection Engineer

Jackson Li

Full-time · Job · Berlin

About the role

We just closed our Series A and are scaling fast, and one of the first things enterprise security teams ask before signing is whether our models can be tricked into leaking their system prompts or internal instructions. We need a senior engineer to make sure the answer is a confident no. You'll build detection systems that identify prompt exfiltration attempts in real time, patterns where a user is probing for system prompt content, internal tool definitions, or configuration details, and block or flag them before a response goes out. You'll work closely with our security and research teams, running adversarial testing against your own detection systems to keep them ahead of new exfiltration techniques as they emerge.

Responsibilities

  • Build real-time detection for prompt exfiltration and system prompt leakage attempts
  • Run adversarial red-team testing against detection systems
  • Partner with security to define response and blocking policy
  • Stay current on emerging exfiltration techniques and update detection accordingly

Requirements

  • 6+ years in ML security, NLP, or adversarial robustness research
  • Strong hands-on experience with the OpenAI API and prompt engineering
  • Experience with Hugging Face model fine-tuning for classification tasks
  • Track record of adversarial or red-team security work

Benefits

  • Fully remote position
  • Competitive salary plus equity
  • Health and dental insurance
  • Security conference and research budget

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$200k+ / year

AI Expertise

AI & Machine Learning Engineers NLP & Prompt Engineering

Skills

python openai api prompt engineering hugging face

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile