Prompt Engineer (AI)

TL;DR

Prompt Engineer (AI): Owning and maintaining Claude's behavior within Claude Code to ensure a consistent, safe, and high-quality user experience with an accent on prompt tuning and behavioral evaluation. Focus on designing system prompts, leading incident response for behavioral regressions, and iterating rapidly on model-specific prompt strategies to improve developer experience.

Location: Must be based in or able to work from San Francisco, CA; New York City, NY; or Seattle, WA. Role is hybrid with a minimum 25% office attendance requirement.

Salary: $300,000 - $405,000 USD

Company

hirify.global is a public benefit corporation focused on creating safe, steerable, and reliable AI systems through large-scale research.

What you will do

• Manage Claude Code's system prompts to ensure consistent and well-tuned behaviors across new model releases.
• Lead incident response for behavioral or policy concerns in coordination with product and safeguards teams.
• Translate feature requirements and user feedback into effective prompts and behavioral specifications.
• Build and maintain behavioral evaluations to measure model performance and detect regressions.
• Create documentation and guides for optimal prompting strategies tailored to specific model snapshots.
• Collaborate across organizational boundaries to scale prompting and evaluation best practices.

Requirements

• Must be able to work from San Francisco, NYC, or Seattle with a minimum 25% in-office requirement.
• Strong proficiency in Python and TypeScript.
• Experience as a power user of agentic coding tools with intuition for model capabilities.
• Ability to drive production changes independently in a fast-paced environment.
• Bachelor's degree in a related field or equivalent experience.
• Must be authorized to work in the US (visa sponsorship available for qualified candidates).

Nice to have

• Experience with agent scaffold architectures and model training processes.
• Background in driving behavioral evaluations for AI products.
• Deep interest in AI safety and interpretability.

Culture & Benefits

• Competitive salary and benefits package.
• Flexible working hours to support work-life balance.
• Supportive environment with generous vacation and parental leave policies.
• Opportunity to work on high-impact, large-scale AI research projects.
• Collaborative office culture focused on empirical AI science.