Research Scientist, Gemini Safety (AI)

TL;DR

Research Scientist, Gemini Safety (AI): Apply and develop data and algorithmic solutions to advance the safety and fairness behavior of hirify.global's latest Gemini models with an accent on text-to-text, image/video/audio-to-text modalities and agentic capabilities. Focus on improving Gemini’s adversarial robustness, designing high quality evaluation protocols and driving innovation of Supervised Fine Tuning and Reinforcement Learning fine-tuning at scale.

Location: Zurich, Switzerland

Company

hirify.global is a team of scientists, engineers, machine learning experts working together to advance the state of the art in artificial intelligence.

What you will do

• Post-training / instruction tuning state of the art LLMs, focusing on text-to-text, image/video/audio-to-text modalities and agentic capabilities
• Explore data, reasoning and algorithmic solutions to make sure Gemini Models are safe, maximally helpful, and work for everyone.
• Improve Gemini’s adversarial robustness, with a focus on high-stakes abuse risks.
• Design and maintain high quality evaluation protocols to assess model behavior gaps and headroom related to safety and fairness.
• Develop and execute experimental plans to address known gaps, or construct entirely new capabilities

Requirements

• PhD in Computer Science, a related field, or equivalent practical experience.
• Significant LLM post-training experience.

Nice to have

• Experience in Reward modeling and Reinforcement Learning for LLMs Instruction tuning
• Experience with Long-range Reinforcement learning
• Experience in areas such as Safety, Fairness and Alignment
• Track record of publications at NeurIPS, ICLR, ICML
• Experience with JAX

Culture & Benefits

• The team has a strong culture of support, dedication and collaboration.
• Committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law.