Researcher, Misalignment Research (AI)

TL;DR

Researcher, Misalignment Research (AI Safety): Identifying, quantifying, and understanding future AGI misalignment risks with an accent on adversarial evaluations and system-level stress testing. Focus on designing worst-case demonstrations, building automated red-teaming infrastructure, and researching failure modes of alignment techniques.

Location: San Francisco, USA

Salary: $295K – $445K + Equity

Company

An AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Design and implement worst-case demonstrations to make AGI alignment risks concrete for stakeholders.
• Develop adversarial and system-level evaluations and drive their adoption across hirify.global.
• Create automated tools and infrastructure to scale automated red-teaming and stress testing.
• Conduct research on failure modes of alignment techniques and propose improvements.
• Publish influential papers to shift safety strategy and reduce existential AI risk.
• Partner with engineering, research, policy, and legal teams to integrate findings into product safeguards.

Requirements

• 4+ years of experience in AI red-teaming, security research, adversarial ML, or related safety fields.
• Strong research track record including publications, open-source projects, or high-impact internal work.
• Fluency in modern ML/AI techniques and comfort hacking on large-scale codebases.
• Ability to communicate complex findings into actionable recommendations for technical and non-technical audiences.
• Must be based in San Francisco

Nice to have

• Ph.D., master’s degree, or equivalent experience in computer science, machine learning, security, or a related discipline.

Culture & Benefits

• Mission-driven environment focused on the safe deployment of AGI.
• Culture of rigorous, impact-oriented safety work.
• Collaborative cross-functional projects spanning research, engineering, and policy.
• Competitive compensation including equity offers.