Frontier AI Safety Researcher

Concordia AI; Singapore; In loco; SGD 120.000 - 180.000; Tempo pieno

Descrizione del lavoro

Concordia AI is seeking researchers to advance frontier safety research for large models and AI agents. You will help build safety benchmarks, perform red-teaming, and develop risk modeling to mitigate loss-of-control and misuse risks.

You will translate findings into practical safety solutions and contribute to real-world AI governance initiatives. The role emphasizes independent work within a mission-driven team focused on creating robust evaluation methods, scalable safety platforms, and

Competenze

• Must have strong foundations in data structures and algorithms and be able to apply Python for algorithm design and data analysis.
• Excellent logical reasoning and technical writing skills to draft research proposals and experimental reports.
• Strong Chinese reading and writing skills, with proficient spoken Chinese for smooth communication.
• Experience with large model deployment and risk analysis is desirable.

Mansioni

• Drive frontier safety research for large models and AI agents.
• Develop safety benchmarks and risk modeling for frontier AI domains.
• Research red-teaming attack and defense algorithms and mitigation strategies.
• Translate research outcomes into practical safety solutions and real-world applications.

Conoscenze

Python

Data structures & algorithms

Technical writing

Chinese language

Formazione

Bachelor's degree or above

Strumenti

API usage

Descrizione del lavoro

Concordia AI is seeking researchers to advance frontier safety research for large models and AI agents. You will help build safety benchmarks, perform red-teaming, and develop risk modeling to mitigate loss-of-control and misuse risks.

You will translate findings into practical safety solutions and contribute to real-world AI governance initiatives. The role emphasizes independent work within a mission-driven team focused on creating robust evaluation methods, scalable safety platforms, and