Research Engineer, Frontier Safety Mitigations, DeepMind

Google DeepMind is a pioneering AI lab focused on advancing AI development to solve complex global challenges. In this role, you will be accountable for the safety and behavior of Google DeepMind’s latest Gemini models, focusing on critical domains such as CBRN and Cybersecurity, while developing and implementing safety mitigations. Responsibilities: Develop high quality evaluations that capture risks arising in frontier safety domains, such as cybersecurity and CBRN; Design, implement, and productionalize a range of safety mitigations, including in-model approaches (e.g., Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training recipes) and out-of-model solutions (e.g., logging, monitoring); Own the data and evaluation pipeline to measure the effectiveness of our mitigations Qualifications: 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; 1 year of experience with software design and architecture Required Skills: Software Development, Programming Languages, Software Testing, Software Design, Software Architecture, Large Language Model Development, Safety Evaluation Methodologies, Safety, Alignment, Frontier Safety Framework, Adversarial Attacks, Mitigation Strategies, Research to Product Development, CBRN Domain Knowledge, Cybersecurity, Supervised Fine-Tuning, Reinforcement Learning, Data, Evaluation Pipeline