Research Engineer, Frontier Red Team (AI)

TL;DR

Research Engineer, Frontier Red Team (AI): Building and evaluating model organisms of autonomous AI systems and developing defensive agents to counter them with an accent on AI capabilities research, security, and policy. Focus on designing and building autonomous AI systems, creating evals and training environments, and developing defensive agents.

Location: Hybrid in San Francisco, CA, USA, requiring office attendance at least 25% of the time. Visa sponsorship is available.

Salary: $350,000–$850,000 USD

Company

hirify.global is a public benefit corporation focused on creating reliable, interpretable, and steerable AI systems for safety and societal benefit.

What you will do

• Design and build autonomous AI systems that use tools and operate across diverse environments to understand and defend against advanced adversarial AI.
• Create evaluations and training environments to understand and shape agent behavior.
• Develop defensive agents capable of detecting, disrupting, or outcompeting adversarial AI systems.
• Interface Claude with hardware platforms like robotics to understand cyberphysical risks and defenses.
• Translate technical findings into demonstrations and artifacts to inform policymakers and the public.
• Collaborate with external experts in cybersecurity, national security, and AI safety.

Requirements

• Strong software engineering skills, particularly in Python.
• Experience building and working with LLM-based agents or autonomous systems.
• Driven to find solutions to ambiguously scoped, high-stakes problems.
• Ability to design and run experiments quickly, iterating fast toward useful results.
• Thrives in collaborative environments, including pair programming.
• Deep care for AI safety and desire for real-world impact on navigating advanced AI.

Nice to have

• Experience with reinforcement learning, self-play, or multi-agent systems.
• Experience with robotics, hardware interfaces, or cyberphysical systems.
• Track record of building demos or prototypes that communicate complex technical ideas.
• Familiarity with AI safety research and threat modeling for advanced AI systems.

Culture & Benefits

• Focus on high-impact AI research as a single cohesive team.
• Competitive compensation and benefits, with optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours and a collaborative office space.
• Values impact, steerable, trustworthy AI, and an empirical science approach to AI research.
• Frequent research discussions and emphasis on communication skills.