AI/LLM Safety Engineer — Guardrails & Red Teaming

Propio; United States; Remote; USD 90,000 - 130,000; Full time

Job summary

Propio is seeking an AI/LLM Safety Engineer to ensure that AI models operate safely in production. The role involves designing safety evaluations, leading red-teaming exercises, and building guardrails.

Ideal candidates will have a degree in a relevant field and 4+ years of software development experience, particularly with ML/LLM systems. Strong programming skills in Python and understanding of AI safety principles are crucial. Propio is dedicated to enhancing communication accessibility through AI-powered tools.

Qualifications

• 4+ years building production software with experience in ML/LLM systems.
• Solid understanding of LLMs and their safety implications.
• Demonstrated ability to threat-model AI workflows.

Responsibilities

• Design and maintain a safety evaluation framework.
• Lead structured red-teaming exercises.
• Build and iterate on guardrail logic.
• Instrument AI features for safety monitoring.

Skills

Python programming

Threat modeling

Machine Learning

Security mindset

Software engineering

Understanding of LLMs

Education

Bachelor's or Master's degree in Computer Science, Software Engineering, Cybersecurity

Tools

Safety tooling (garak, PyRIT, etc.)

Job description

Propio is seeking an AI/LLM Safety Engineer to ensure that AI models operate safely in production. The role involves designing safety evaluations, leading red-teaming exercises, and building guardrails.

Ideal candidates will have a degree in a relevant field and 4+ years of software development experience, particularly with ML/LLM systems. Strong programming skills in Python and understanding of AI safety principles are crucial. Propio is dedicated to enhancing communication accessibility through AI-powered tools.