AI Safety Specialist: Guardrails & Robustness for LLMs

Hyphen Connect; Geelong; Presencial; AUD 90.000 - 150.000; Jornada completa

Descripción de la vacante

Hyphen Connect is seeking an AI Safety Specialist to strengthen the security and reliability of language models. You will lead adversarial testing, implement guardrails for autonomous tools, and help align AI behavior with ethical principles.

You will work with cross‑functional teams to refine safety frameworks, contribute to constitutional AI concepts, and support RLHF alignment pipelines to advance responsible AI deployment. Based in Geelong, this role shapes safer AI at scale across products.

Formación

• Experience in safeguarding AI systems against adversarial inputs.
• Familiarity with jailbreak taxonomies and red-teaming workflows.
• Ability to identify and reason about edge cases in AI behavior.

Responsabilidades

• Conduct adversarial testing on LLMs and multimodal agents.
• Implement guardrails and real-time filtering for autonomous tool use.
• Contribute to constitutional AI principles and RLHF alignment pipelines.

Conocimientos

Adversarial ML

Prompt engineering

Cybersecurity

Edge-case analysis

Herramientas

Red-teaming frameworks

Guardrails tooling

Descripción del empleo

Hyphen Connect is seeking an AI Safety Specialist to strengthen the security and reliability of language models. You will lead adversarial testing, implement guardrails for autonomous tools, and help align AI behavior with ethical principles.

You will work with cross‑functional teams to refine safety frameworks, contribute to constitutional AI concepts, and support RLHF alignment pipelines to advance responsible AI deployment. Based in Geelong, this role shapes safer AI at scale across products.