Research Scientist, AI Safety and Security - Singapore

GOOGLE ASIA PACIFIC PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Google Asia Pacific PTE. LTD.

is seeking a Research Scientist to join a focused effort on proactive threat mitigation, adversarial ML, and agentic security, to strengthen next-generation trustworthy AI models and intelligent agents. You will work on ML foundations, continual learning, interpretability, and evaluation benchmarks, collaborating with international teams to translate research into robust production systems.

Qualifications

• PhD or equivalent experience in CS or related field.
• Experience in ML safety, adversarial ML, and frontier AI evaluation.
• One or more peer-reviewed publications in conferences/journals (e.g., NeurIPS, ICML, CVPR).
• Strong programming and experimental design skills.

Responsibilities

• Advance foundational ML research in model robustness, continual learning, interpretability, and multiobjective optimization.
• Design evaluation protocols, scenario-based benchmarks, and stress-testing methods for frontier AI capabilities.
• curate advanced datasets and run fine-tuning/optimization experiments to enhance model resilience.
• Collaborate with regional engineering hubs, core product teams, and academia to translate proofs-of-concept into robust production solutions.
• Publish groundbreaking research and engage with academic and industry communities.

Skills

Adversarial ML

AI safety

Research

Multi-objective optimization

Publications

Education

PhD in Computer Science or related field

Tools

Python

Experimentation frameworks

Job description

Job description

As a Research Scientist, you will join a specialized research effort dedicated to proactive threat mitigation, adversarial machine learning, and agentic security. Our team operates at the trustworthy AI, focusing on securing next-generation AI models and intelligent agents against emerging threats.

In this role, you will focus on the machine learning foundations of AI safety, developing innovative techniques, continual learning, and interpretability to prevent safety drift and enhance intrinsic model robustness. You will co-develop advanced evaluation benchmarks, working alongside academic institutions and global engineering teams to provide research that will form the basis of next-generation trustworthy AI capabilities.

Qualifications

Job responsibilities

• Drive foundational machine learning research in model robustness, continual learning, interpretability, and multiobjective optimization to advance trustworthy AI.
• Design and develop rigorous evaluation protocols, scenario-based benchmarks, and stress-testing methodologies to assess frontier AI capabilities and multi-agent consensus.
• Curate advanced datasets and conduct fine-tuning or optimization experiments to enhance model resilience against emerging threats and ensure adherence to safety constraints.
• Collaborate extensively with regional engineering hubs, core product teams, and academic partners to transition theoretical proofs-of-concept into robust production solutions.
• Publish groundbreaking research in machine learning venues and actively participate in academic and industry research communities

Minimum qualifications

PhD degree in Computer Science, a related field, or equivalent practical experience.

Experience in machine learning, adversarial machine learning or evaluating frontier AI systems, which includes but not limited to supervised learning, unsupervised learning and reinforcement learning, ML interpretability, adversarial robustness, ML safety, generative models, agentic AI, multi-object optimization.

One of more scientific publication submission(s) for conferences, journals, or public repositories (such as CVPR, ICCV, NeurIPS, ICML, ICLR, etc.).

Preferred qualifications

• Experience with general purpose programming languages (e.g., Python).
• Experience investigating emerging technical threats (e.g., automated scams, deepfake generation, or rogue agent vulnerabilities) and designing robust, proactive defense mechanisms.
• Demonstrated expertise in adversarial machine learning, AI agent security, data poisoning, prompt injection, and model backdoor detection.
• Strong background in applying a security mindset to artificial intelligence, including debugging complex ML failure modes, reverse engineering model behaviors, and red-teaming frontier AI systems.
• First-authored publications in top machine learning, safety/security tracks in machine learning or AI conferences, or HCI conferences.