AI Security Researcher

PERSOL SINGAPORE PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

PERSOL SINGAPORE PTE. LTD. is seeking a PhD-level AI safety researcher to advance safety for AI systems, including multimodal LLMs and AI agents.

The role emphasizes research output, tool design for safety, and collaboration with academia and industry to bridge theory and practice. Responsibilities include contributing to safety governance, privacy protection, and alignment strategies to support Huawei's product roadmap.

Qualifications

• PhD required in Computer Science, AI or related field.
• Strong publication record in top-tier security or AI venues.
• Proficiency in Python; experience with other languages is a plus.

Responsibilities

• Conduct research on cutting-edge AI safety technologies (multimodal LLMs, AI agents) focusing on safety alignment and privacy protection.
• Design and implement tools for safety such as content moderation, monitoring, explainability, and violation detection.
• Collaborate with academic and industrial partners to translate research into practical solutions.
• Participate in AI standardization efforts and contribute to open ecosystem development.
• Provide strategic guidance on AI safety governance and privacy policies to support the product roadmap.

Skills

Python

Research publication

Security/AI knowledge

Education

Ph.D. in Computer Science/AI

Tools

TensorFlow

PyTorch

MindSpore

Job description

Job Description

• Conduct research on key cutting-edge technologies to enhance the safety of AI systems, including (multimodal) large language models and AI agents. Focus areas include, but are not limited to, safety alignment, robustness against adversarial input such as jailbreaking, and data privacy protection.
• Design and implement tools and modules to support AI safety, such as content moderation, runtime monitoring, explainability frameworks, and violation detection mechanisms, with the goal of improving the safety and reliability of Huawei's AI products and services.
• Collaborate with academic institutions to bridge the gap between research and industrial application, facilitating the translation of theoretical advances into practical solutions.
• Participate in relevant AI standardization initiatives and contribute to the development of open, collaborative ecosystems.
• Provide strategic guidance and technical insight on AI safety, including governance frameworks, security protocols, and privacy protection policies, to support Huawei's product and service roadmap.

Skills / Qualifications

• Ph.D. in Computer Science, Artificial Intelligence, or a related field.
• Strong publication record in top-tier security or AI conferences (e.g., CCS, IEEE S&P, USENIX Security, NDSS, NeurIPS, ICML, ICLR, AAAI), or other relevant venues.
• Proficient in Python; experience with additional programming languages is a plus.
• Practical experience with deep learning frameworks such as TensorFlow, PyTorch, or MindSpore.