Researcher, Recursive Self-Improvement Preparedness (AI)

TL;DR

Researcher, Recursive Self-Improvement Preparedness (AI): Support preparations for recursive self-improvement by reasoning about future AI problems and implementing mitigations with an accent on AI R&D risk measurement, data-poisoning defenses, model behavior science, and model transparency. Focus on designing experiments, building scrappy prototypes, prototyping verification mechanisms, and prioritizing high-impact work.

Location: San Francisco (onsite)

Salary: $295K – $445K

Company

hirify.global is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Carefully consider future problems hirify.global might face and prepare for them.
• Turn open-ended objectives into concrete directions and prioritize most useful work to start now.
• Execute quickly by building scrappy prototypes and iterating on them.
• Secure buy-in from other staff and communicate work clearly.
• Collaborate with or manage other staff to scale efforts rapidly.

Requirements

• Exceptional technical executor.
• Strong strategic and research taste for prioritizing in weak feedback domains.
• Passionate about mitigating risks of recursive self-improvement.
• Driven to do work that most positively impacts AI development future.
• US-based candidates; background checks per applicable law including San Francisco Fair Chance Ordinance.

Nice to have

• Experience in ML research, AI alignment, AI verification, or related domains.

Culture & Benefits

• Equal opportunity employer committed to diversity and inclusion.
• Reasonable accommodations for applicants with disabilities.
• Focus on safety and human needs at core of AI development.