Applied Safety Research Engineer (AI)

TL;DR

Applied Safety Research Engineer (AI): Developing methods for safety evaluations of AI models with an accent on representative test data generation, realistic user behavior simulation, and grading accuracy validation. Focus on improving model safety across misuse, prompt injection, and user well-being through productionized evaluation pipelines and collaboration with Policy and Enforcement.

Location: Expect all staff to be in one of our San Francisco offices at least 25% of the time.

Salary: $320,000 - $405,000 USD

Company

hirify.global’s mission is to create reliable, interpretable, and steerable AI systems.

What you will do

• Design and run experiments to improve evaluation quality by developing methods to generate representative test data and simulate realistic user behavior.
• Research how different factors impact model safety behavior.
• Analyze evaluation coverage to identify gaps and inform where we need better measurement.
• Productionize successful research into evaluation pipelines that run during model training, launch and beyond.
• Collaborate with Policy and Enforcement to translate real-world harm patterns into measurable evaluations.
• Build tooling that enables policy experts to create and iterate on evaluations.

Requirements

• Have 4+ years of software engineering or ML engineering experience.
• Are proficient in Python and comfortable working across the stack.
• Have experience building and maintaining data pipelines.
• Are comfortable with data analysis and can draw insights from large datasets.
• Have experience with LLMs and understand their capabilities and failure modes.
• We require at least a Bachelor's degree in a related field or equivalent experience.

Culture & Benefits

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.
• Lovely office space in which to collaborate with colleagues.