AI Safety Specialist (AI Engineering)
Tasks
- Align AI behavior with ethical principles
- Conduct adversarial testing on LLMs
- Develop constitutional AI principles
- Implement guardrails and real time filtering
- Support RLHF alignment pipelines
Perks/Benefits
- N/A
Skills/Tech-stack
Adversarial Machine Learning | Automated Red Teaming | Cybersecurity | Ethical AI | Guardrails | Human Feedback | Jailbreak Taxonomy | Language Models | Large Language Models | Learning from Human Feedback | Machine Learning | Multimodal agents | Prompt engineering | Real Time | Real-time filtering | Red Teaming | Reinforcement Learning | Reinforcement Learning from Human Feedback | Time Filtering
Education
N/A
Roles
AI | AI Engineer | AI Safety Specialist | Engineer | Safety Specialist | Specialist
Related jobs
-
Security Operations Engineer HKD 67K-92KAccess Control | Cybersecurity | Data Loss Prevention | Data loss | Endpoint protectionDiscounts | Employee assistance program | Flexible work arrangements | Growing Families policy | Learning and development programsSenior-level Full TimeChadstone, Victoria, AU11d ago
-
Access Management | Ansible | CI/CD | Configuration Management | Container SecurityAnnual leave | Life insurance | Medical, dental, and vision insurance | Professional development allowance | Remote working policySenior-level Full TimeHong Kong16d ago
-
AI Governance | AI Security | Agile | Algorithms | Artificial IntelligenceSenior-level Full TimeHong Kong18d ago
-
Digital & Intelligent Specialist (Risk Management) HKD 312K-586KAPI Orchestration | Agent Frameworks | Algorithms | Chain-of-Thought | Chain-of-Thought promptingMid-level Full TimeHong Kong24d ago
-
API Integration | Artificial Intelligence | IT Audit | IT Security | Knowledge BaseSenior-level Full TimeHong Kong1mo ago
-
AI Security Engineer HKD 112K-162KAPI Integration | Agent Orchestration | Agent systems | Authentication Security | AutomationAnnual leave | Crypto visa card | Extended medical coverage for dependents | Hybrid or remote work | Medical insuranceSenior-level Full TimeHong Kong, Hong Kong SAR1mo ago
-
800-53 | Blockchain Security | Code auditing | Cybersecurity | HIPSMid-level Full TimeHong Kong, Hong Kong SAR, Hong …1mo ago
-
Application Security | Attack Simulation | Automation | Cloud Security | Cyber SecurityExecutive-level Full TimeHK-TWO ES 7/F, Hong Kong1mo ago