Applied Research Engineer, Frontier Safety Mitigations

Google LLC; Mountain View, San Francisco (CA, CA); Vor Ort; USD 174.000 - 252.000; Vollzeit

Zusammenfassung

Google DeepMind is recruiting a Share Research Engineer for the Frontier Safety Mitigations team. The role focuses on building robust, end-to-end defenses against frontier-model risks and contributing to the Frontier Safety Framework commitments.

You will work on de-risking model launches, creating evaluations, red-teaming, and deploying mitigations at scale. The position emphasizes translating research into practical safety solutions, with collaboration across global teams and a strong emphasis

Qualifikationen

• Bachelor’s degree or equivalent practical experience.
• 5 years of experience with software development in one or more programming languages.
• 3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
• Master's degree or PhD in Computer Science or a related technical field.
• Experience in Large Language Model (LLM) development, fine-tuning, or safety evaluation methodologies.
• Experience taking research from concept to product.
• Experience in areas such as Safety and Alignment.

Aufgaben

• Build classifiers and data pipelines to detect misuse from evaluation to rapid iteration.
• Build cross-context monitoring to detect coordinated harms across sessions.
• Implement semi-automated account-level response systems using production signals.
• Evaluate and secure agentic AI with threat models and testing environments.
• Advance automated red-teaming and adversarial robustness research.

Kenntnisse

Software development

Testing and QA

Architecture design

LLM safety

Ausbildung

Bachelor's degree or equivalent

Master's/PhD preferred

Jobbeschreibung

Google DeepMind is recruiting a Share Research Engineer for the Frontier Safety Mitigations team. The role focuses on building robust, end-to-end defenses against frontier-model risks and contributing to the Frontier Safety Framework commitments.

You will work on de-risking model launches, creating evaluations, red-teaming, and deploying mitigations at scale. The position emphasizes translating research into practical safety solutions, with collaboration across global teams and a strong emphasis