Head of Engineering (Frontier Safety)

About Us

FAR.AI is a non-profit AI research institute working to ensure advanced AI is safe and beneficial for everyone. Our mission is to facilitate breakthrough AI safety research, advance global understanding of AI risks and solutions, and foster a coordinated global response.

Since our founding in July 2022, we've grown to 50+ staff , published 40+ academic papers , and convened leading AI safety events . Our work is recognized globally, with publications at premier venues such as NeurIPS, ICML including a Best Paper Honorable Mention in 2026 , and ICLR, and features in the Financial Times , Nature News , Wired Magazine and MIT Technology Review . We conduct pre-deployment testing on behalf of frontier developers such as OpenAI, independent evaluations for governments including the EU AI Office , and publish the AI Security Leaderboard based on our red-teaming expertise. We help steer and grow the AI safety field through developing research roadmaps with renowned researchers such as Yoshua Bengio; running FAR.Labs , an AI safety-focused co-working space in Berkeley housing 40+ members; and supporting the community through targeted grants to technical researchers.

Head of Engineering (Frontier Safety)

FAR.AI is seeking a Head of Engineering for its Frontier Safety division, which runs one of the world’s most impactful frontier AI testing programs. This role focuses on building the engineering and execution engine that enables and empowers the division’s work across testing, evaluations, tools, products, services, and research. The systems and the team you build will enable the division to execute on high-stakes engagements with frontier AI companies and leading governments, and provide these stakeholders critical insights and tools, aiming to multiply the world’s rate of progress via testing towards safe AI. This is an opportunity to shape how AI safety is practiced at the frontier, with real impact on industry behavior, governments, public awareness, and global norms.

About the Frontier Safety Division

FAR.AI ’s Frontier Safety division exists to materially raise the bar for safety and security of the most capable AI systems in the world. We intend to be the tip of the spear in AI safety: the team that consistently finds the failures others miss, converts these into mitigations by frontier developers, and sets the standard that labs and governments converge on.

The division grew out of FAR.AI 's red team, and is expanding rapidly into loss of control testing, deeper evaluations, and safeguards. From that base, we discover issues, drive their mitigation, and, where a gap in safeguards is blocking a fix, build the missing technical capacity ourselves. What we learn from building and studying safeguards then feeds back into new ways of finding vulnerabilities.

We are already one of the leading independent red-teaming organizations globally. We use our understanding of weaknesses in models to advise frontier developers on mitigations, work with governments on building evaluation infrastructure and technical capability, and to guide our own research and grantmaking for improving model security. Our work has helped most Western frontier model developers improve safeguards through pre- and post-deployment testing (e.g., OpenAI, Anthropic, and Google) and pioneered new industry standards (e.g. the FAR.AI Minimal Standard for Safeguards ). We are also increasingly embedded in high-leverage government efforts (e.g., leading a consortium building CBRN evaluations for the European Commission/EU AI Office, and collaborating with the UK AI Security Institute).

" FAR.AI 's pre-deployment testing of GPT-5 series models identified failure modes and mitigations, improving the security of our model releases. " – Senior Technical Program Manager, OpenAI

“ FAR.AI have been a trusted and thoughtful collaborator for us, and they have progressed the state of frontier red-teaming through research like STACK. We expect this to be a high impact role and are excited to explore collaborations with the successful candidate.” – Xander Davies, Technical Lead, Red Team at UK AISI

The Role

As Head of Engineering (Frontier Safety), you will be the senior technical owner of engineering for the FAR.AI Frontier Safety division, reporting to Kellin Pelrine with a dotted line to Edward Yee . You will partner closely with Kellin, the division’s technical lead, translating broader technical strategy and priorities into a world-class engineering organization, systems, and execution. You will build the engineering team and the systems to test critical safeguards of the next generation of AI models, evaluate their most dangerous capabilities, and help close the gaps we find.

Success for the division looks like new vulnerabilities found, a rapidly accelerating stream of vulnerabilities fixed, and safeguards strengthened. We work with leading frontier labs and governments globally to make this happen. Towards those goals, success for Engineering looks like abundant technical capacity and leverage in a division that aims to scale the level of our testing, research, products, and overall impact by 10-100x or more per year. This means new technical capabilities move rapidly from prototype to robust deployment; infrastructure scales reliably while hiding underlying complexity; and recurring workflows become increasingly autonomous and effective. Systems your team builds will enable our high-stakes engagements, accelerate cutting-edge AI security research, and power the tools, products, and services that let us and our partners red-team and evaluate the frontier continuously and comprehensively. Together, they will form the scalable foundation for a relentless, high-velocity division working to make advanced AI systems safer.

Why are we hiring for this role?

Our division has grown from a red team into a broader frontier safety program, and our engineering capacity has not kept pace. Today, much of our engineering is done by researchers and red-teamers alongside their main work. We are hiring a Head of Engineering to build that function, starting with a small team and growing from there, so that new research reaches production quickly and our testing can grow much faster than our headcount. For the right person, this is a chance to build the engineering behind one of the leading independent AI safety testing efforts almost from the ground up.

Key Responsibilities

We expect this role to start with a small team and build from there. In practice, this role spans:

• Building a scalable technical engine. Your leadership will take our already state-of-the-art red-teaming stack to the next level and extend it to the division's evaluations, loss-of-control testing, and safeguards work, building tooling, products, services, evals, agents, and a self-improving workflow that exponentially multiplies output:
• Build and scale red-teaming tools and products that improve speed, coverage, and importance of findings;

• Operationalize and scale systems that advance state-of-the-art attacker simulation and output severity evaluation;

• Maintain and evolve internal vulnerability databases, statistical analysis tools, and reporting infrastructure;

• Develop agentic systems, including automated red-teaming agents that systematically explore the attack space, agents that identify and automatically integrate new public jailbreaks, and agents that automate workflows to accelerate the division broadly;

• Build, test, and refine sandboxing architecture that enables rapid and thorough evaluation of the strongest AI systems, while ensuring strong security appropriate for high-stakes risk domains like cybersecurity and autonomy;

• Extend our infrastructure and tooling to support the division's CBRN and cyber evaluations and loss-of-control testing;

…