Research Engineer, AI Safety & Alignment

TL;DR

Research Engineer, AI Safety & Alignment: Conduct foundational research to enhance AI safety and alignment with an accent on developing evaluation methodologies and mitigating risks. Focus on implementing cutting-edge techniques and collaborating with teams to translate research into practical solutions.

Location: Redwood City, CA

Compensation Range: $225K - $400K

Company

hirify.global empowers people to connect, learn and tell stories through interactive entertainment.

What you will do

• Develop and implement novel evaluation methodologies and metrics for AI safety and alignment.
• Research techniques for model alignment, value learning, and interpretability.
• Conduct adversarial testing to uncover vulnerabilities in models.
• Analyze and mitigate biases and harmful behaviors in AI models.
• Collaborate with engineering and product teams to implement safety solutions.
• Contribute to the academic community through publications and presentations.

Requirements

• PhD or equivalent experience in Computer Science, Machine Learning, or related field.
• Experience with GPUs and data pipelines.
• Strong understanding of modern machine learning techniques, particularly transformers and reinforcement learning.
• Passionate about responsible AI development and solving safety challenges.

Nice to have

• Experience with product experimentation and A/B testing.
• Familiarity with ML deployment and orchestration (Kubernetes, Docker).
• Research in AI safety, alignment, or ethics.
• Publications in relevant academic journals.