About this role
This role addresses the need to scale the engineering and execution infrastructure for FAR.AI's frontier AI red-teaming programs. The core objective is to build the systems and team that enable the red team to conduct high-stakes engagements with frontier AI companies and governments. This work provides critical insights and tools necessary to advance the field of safe AI by consistently identifying failures in large models and setting industry standards for security. The successful candidate will be instrumental in shaping how AI safety is practiced at the frontier, influencing industry behavior and global norms.
The team's mission is to materially raise the safety and security bar for the most capable AI systems globally. This involves acting as the spearhead in AI safety by finding weaknesses others overlook, leading to real mitigations, and establishing a standard that other labs and governments adopt. This position directly supports the organization's efforts to advise developers, guide internal research, and inform public discourse regarding AI risks.
This role is ideal for an individual who thrives on building robust engineering solutions for complex, high-impact problems. It requires someone who can translate complex safety research into actionable testing tools and scalable execution pipelines. Candidates who are motivated by making a tangible impact on the security and alignment of frontier AI models and are comfortable operating at the intersection of research, engineering, and policy will find this opportunity highly suitable.
What you will do
- Build the engineering and execution engine that supports the red team's work across testing, tools, products, and services.
- Develop systems that enable the division to execute on high-stakes engagements with frontier AI companies and governments.
- Provide stakeholders with critical insights and tools derived from red-teaming activities.
- Consistently create progress toward safe AI by executing on red-teaming objectives.
- Shape how AI safety is practiced at the frontier through the development of core infrastructure.
What you need
- Demonstrated experience in building engineering capabilities for complex research programs is required.
- The candidate must be capable of developing tools and products that facilitate advanced AI safety testing.
- Experience in executing high-stakes engagements involving frontier AI developers and government bodies is necessary.
- A strong background in translating deep understanding of model weaknesses into practical testing methodologies is essential.
- Proficiency in engineering the systems required for pre-deployment testing across various AI model types is a must.
- Experience in guiding research roadmaps related to AI security and alignment would be beneficial.
Nice to have
- Experience with adversarial attack methodologies
- Background in AI safety research
Benefits
- $225K – $350K salary
Skills and tech stack
Questions candidates ask
What is the remote policy for this role?
The position is listed as Remote (International). The posting does not specify detailed remote work policies.
What is the compensation range for this role?
The salary offered for this Head of Engineering (Red Team) role ranges from $225K to $350K.
What is the primary technology stack involved?
The posting does not explicitly list specific tools, languages, or frameworks used in the engineering stack.
What is the team structure like?
The role focuses on building the engineering and execution engine that empowers the red team's work across testing, tools, products, services, and research.