AI Safety & Alignment Research Engineer

character; Redwood City (CA); On-site; USD 120,000 - 150,000; Full time

Job summary

Character in Redwood City, California is seeking a Research Engineer to tackle critical challenges in AI safety and alignment. As a Research Engineer, you'll develop methodologies to evaluate and improve model safety, conduct adversarial testing, and translate research into scalable solutions.

The ideal candidate holds a PhD in Computer Science or a related field, has experience with GPUs, and is passionate about responsible AI development. Join us to contribute to making AI systems safer and more aligned with human values.

Qualifications

• PhD (or equivalent experience) in Computer Science, Machine Learning, or related field.
• Strong understanding of modern machine learning techniques and their safety implications.
• Clear production-facing and training code writing experience.

Responsibilities

• Develop and implement evaluation methodologies for AI safety.
• Conduct adversarial testing to uncover model vulnerabilities.
• Collaborate with teams to apply safety research into products.

Skills

PhD in Computer Science

Clear and clean code writing

Experience with GPUs

Experience with data pipelines

Understanding of machine learning techniques

Passion for responsible AI development

Education

PhD in a relevant field

Tools

Kubernetes

Docker

Job description

Character in Redwood City, California is seeking a Research Engineer to tackle critical challenges in AI safety and alignment. As a Research Engineer, you'll develop methodologies to evaluate and improve model safety, conduct adversarial testing, and translate research into scalable solutions.

The ideal candidate holds a PhD in Computer Science or a related field, has experience with GPUs, and is passionate about responsible AI development. Join us to contribute to making AI systems safer and more aligned with human values.