Skip to main content

AI Safety Specialist (AI Engineering)

Expired
This role has expired and is no longer accepting applications. Browse similar roles →
Hyphen Connect Limited
Australia
remote
Full Time / Permanent

Apply for this job

Posted 3 months ago
This role is expired

These roles are hiring now

View all similar roles →

Senior Data & AI Governance Specialist

Xero
Victoria, VIC
remote
  • Shape data governance & responsible AI frameworks for a global SaaS platform
  • Deep data governance experience with hands-on AI governance expertise
  • AI ethics, data architecture, GDPR, EU AI Act, ISO 27001, policy translation
Posted 5d ago

Associate Director - Model Risk Management

Macquarie Group
Sydney, NSW
hybrid
  • Lead independent validation of financial and risk models
  • Strong experience in model development, validation or quantitative risk
  • Python, R, SAS, MATLAB, SQL; regulatory capital, credit risk models
Posted 5d ago

Principal Security Engineer - AI Security (6-month Contract)

Quantium
Sydney, NSW
hybrid
  • Lead AI security architecture for ML platforms and agentic systems
  • Principal-level hands-on individual contributor role
  • Application security, AI/ML security, cloud-native architecture
Posted 5d ago

Senior Data & AI Governance Specialist

Xero
Sydney, NSW
hybrid
  • Shape data governance & AI governance frameworks for responsible innovation
  • Deep data governance knowledge with recent hands-on AI governance experience
  • AI ethics, data stewardship, GDPR, EU AI Act, policy translation
Posted 5d ago

We are searching for an AI Safety Specialist who will play a crucial role in enhancing the security and robustness of language models. You will ensure the safe deployment of AI systems by conducting adversarial testing, implementing protective measures, and aligning AI behavior with ethical principles.

Responsibilities:

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

Qualifications:

  • Background in cybersecurity, prompt engineering, or adversarial ML.
  • Experience with jailbreak taxonomies and automated red-teaming frameworks.
  • Strong analytical mindset for identifying edge cases.