AI Red Team Engineer
White Circle · Remote · Global ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote
- AI Safety focus
- Python scripting
- LLM Red Teaming
- Equity included
Join White Circle to strengthen the safety and reliability of AI systems. You will conduct hands-on adversarial testing on chatbots, agents, and RAG pipelines, turning discovered failures into actionable evidence for customers and internal teams.
The company processes over one hundred million API calls monthly and fine-tunes its own models. You will work in a small, focused environment where your contributions directly influence product security and go-to-market strategies.
What you'll do
- Red-team LLM systems including chatbots, copilots, and AI agents
- Test for jailbreaks, prompt injection, and data leakage vulnerabilities
- Write Python scripts to automate attacks and score model responses
- Maintain an internal library of prompts, scenarios, and regression tests
- Produce clear reports detailing failure reproduction and severity
- Convert successful attacks into product requirements and regression tests
- Support sales and security reviews with credible evidence of risks
What you'll need
- Background in QA automation, AppSec, or penetration testing
- Strong Python scripting skills for API interaction and automation
- Experience testing APIs, web apps, backends, or SaaS products
- Hands-on experience with LLMs, prompts, RAG, and tool calling
- Understanding of LLM-specific abuse vectors like token-cost exhaustion
- Ability to distinguish real customer risk from low-impact tricks
- Clear written English for reproducible bug reports
- Firm ethical commitment to responsible and legal testing practices
Nice to have
- Experience with Burp Suite, Postman, Playwright, or pytest
- Familiarity with LangChain, LangGraph, or LlamaIndex
- Knowledge of OWASP LLM Top 10 or MITRE ATLAS taxonomies
- Experience testing RAG systems, browser agents, or internal copilots
- Track record in CTFs, red-team competitions, or bounty programs
- Experience building eval pipelines or CI-friendly security tests
Stack
- Python
- LLMs
- RAG
- LangChain
- LangGraph
- LlamaIndex
- Burp Suite
- Postman
- Playwright
- pytest
What you get
- Competitive compensation package with equity
- Flexible Time Off policy
- Language lessons for English or French improvement
- Support for courses, conferences, and skill development
- Provided hardware, subscriptions, and necessary tools
- Biannual team off-sites to locations like the Alps or Marbella
Hiring process
- Intro call with Talent Team
- Test assignment
- Technical interview
- Final call with CEO