Ai Safety Specialist (ai Engineering)

Hyphen Partners

Australia
On-site
Conduct adversarial testing on llms
Implement guardrails for autonomous tools
Experience with jailbreak taxonomies
Hyphen Partners is seeking an AI Safety Specialist to enhance the security and robustness of language models. The role involves conducting adversarial testing, implementing protective measures, and aligning AI behavior with ethical standards

Job Summary

  • The role is crucial for enhancing the security and robustness of language models.
  • You will ensure safe deployment by conducting adversarial testing and implementing protective measures.
  • Responsibilities include developing constitutional AI principles and assisting with RLHF alignment pipelines.

Matching Summary

Match Score: 85

Hyphen Partners is seeking an AI Safety Specialist to enhance the security and robustness of language models. The role involves conducting adversarial testing, implementing protective measures, and aligning AI behavior with ethical standards.

Skills & Requirements

Must-have

  • Conduct adversarial testing on LLMs
  • Implement guardrails for autonomous tools
  • Experience with jailbreak taxonomies

Nice-to-have

  • Strong analytical mindset for edge cases
  • Assist with RLHF alignment pipelines
  • Background in cybersecurity or prompt engineering

Key Requirements

  • Background in cybersecurity, prompt engineering, or adversarial ML
  • Experience with automated red-teaming frameworks

Work Rights

Not specified

Tailored Resume

Cover Letter