Gen AI Red-teaming Engineer.

Qualifications

• Prompt Engineering and LLM security evaluation expertise

• Hands-on experience with AI red-teaming tools like PyRIT, Garak, Giskard

• Experience working with LLM-powered applications and RAG (Retrieval-Augmented Generation) architectures

• Strong Python programming skills and experience with AI security tools

• Knowledge of adversarial machine learning, AI threat models, and security risks

• Background in AI safety, bias detection, and jailbreak detection

• Ability to work in a fast-paced environment and problem-solve complex AI security issues

Responsibilities

• This role focuses on evaluating the security of LLM-based applications by identifying vulnerabilities, adversarial attacks, and bias within AI systems

• Conduct red-teaming exercises on LLM-powered applications to identify security gaps

• Utilize automated AI security tools (e.g., PyRIT, Garak, Giskard) to test AI models

• Implement adversarial machine learning techniques to assess AI robustness

• Work on Prompt Engineering to evaluate AI model behavior and vulnerabilities

• Develop AI safety measures, including bias detection, jailbreak prevention, and AI threat modeling

• Collaborate with teams to enhance AI security and ensure responsible AI development

Full Description

We are looking for a Gen AI Red-teaming Engineer with 5+ years of experience to work onsite in Austin, Texas.

This role focuses on evaluating the security of LLM-based applications by identifying vulnerabilities, adversarial attacks, and bias within AI systems.

Key Responsibilities:

• Conduct red-teaming exercises on LLM-powered applications to identify security gaps.

• Utilize automated AI security tools (e.g., PyRIT, Garak, Giskard) to test AI models.

• Implement adversarial machine learning techniques to assess AI robustness.

• Work on Prompt Engineering to evaluate AI model behavior and vulnerabilities.

• Develop AI safety measures, including bias detection, jailbreak prevention, and AI threat modeling.

• Collaborate with teams to enhance AI security and ensure responsible AI development.

Must-Have Skills:

• Prompt Engineering and LLM security evaluation expertise.

• Hands-on experience with AI red-teaming tools like PyRIT, Garak, Giskard.

• Experience working with LLM-powered applications and RAG (Retrieval-Augmented Generation) architectures.

• Strong Python programming skills and experience with AI security tools.

• Knowledge of adversarial machine learning, AI threat models, and security risks.

• Background in AI safety, bias detection, and jailbreak detection.

• Ability to work in a fast-paced environment and problem-solve complex AI security issues.