Head of Engineering (Red Team)

OpenKrill; United States; Sur place; USD 180 000 - 270 000; Plein temps

Résumé du poste

FAR.AI is seeking a Head of Engineering (Red Team) to scale one of the world’s most impactful frontier AI red‑teaming programs. This role focuses on building the engineering and execution engine that enables and empowers the red team’s work across testing, 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 governments, provide these stakeholders critical insights and tools, and

Responsabilités

• Building a scalable red‑teaming engine: tooling, products, services, evals, agents, and a self‑improving workflow that multiplies output.
• Build and scale internal/external red‑teaming tools and products that improve speed, coverage, and severity of findings.
• Develop agentic red‑teaming systems to automatically and systematically explore the attack space.
• Develop agentic systems to identify new public jailbreaks and other releases, and automatically integrate them into our systems.
• Advance state‑of‑the‑art attacker simulation and output harmfulness evaluation.
• Maintain and evolve internal vulnerability databases, statistical analysis tools, and reporting infrastructure.
• Build systems to empower high‑stakes red‑teaming engagements with frontier AI companies and governments.
• Support public reports, benchmarks, and leaderboards that shape industry norms.
• Contribute to red‑teaming of frontier models (closed‑ and open‑weight), improving testing systems both within particular engagements and turning insights from engagements into advances in our overall systems.
• Build agentic workflows that accelerate the red team broadly.
• Initially managing, mentoring, and supporting a growing elite team of engineering / red‑teaming ICs, with extremely high standards for velocity, rigor, judgment, and impact.
• Plan sprints and lead engineering execution.
• Mentor red team ICs in engineering skills, both in direct 1‑1 settings and by building resources for rapid skill growth and knowledge transfer.
• Manage ICs, supporting and amplifying their impact, setting high standards

Description du poste

ABOUT US

FAR.AI http://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 https://www.far.ai/about/team, published 40+ academic papers https://scholar.google.com/citations?user=FVJ24k8AAAAJ, and convened leading AI safety events https://far.ai/events/. Our work is recognized globally, with publications at premier venues such as NeurIPS, ICML including a Best Paper Honorable Mention in 2026 https://icml.cc/virtual/2026/oral/71065, and ICLR, and features in the Financial Times https://www.ft.com/content/175e5314-a7f7-4741-a786-273219f433a1, Nature News https://www.nature.com/articles/d41586-024-02218-7, Wired Magazine https://www.wired.com/story/jailbreaking-ai-models-google-anthropic-openai-spacexai/ and MIT Technology Review https://www.technologyreview.com/2020/02/28/905615/reinforcement-learning-adversarial-attack-gaming-ai-deepmind-alphazero-selfdriving-cars/. We conduct pre-deployment testing on behalf of frontier developers such as OpenAI, independent evaluations for governments including the EU AI Office https://www.far.ai/news/far-ai-selected-to-lead-eu-ai-act-cbrn-risk-consortium, and publish the AI Security Leaderboard https://leaderboard.far.ai/ based on our red‑teaming expertise. We help steer and grow the AI safety field through developing https://arxiv.org/abs/2405.06624 research https://arxiv.org/abs/2506.20702 roadmaps https://www.researchgate.net/publication/396910034_Open_Technical_Problems_in_Open-Weight_AI_Model_Risk_Management with renowned researchers such as Yoshua Bengio; running FAR.Labs https://www.far.ai/programs/far-labs, an AI safety-focused co‑working space in Berkeley housing 40+ members; and supporting the community through targeted grants https://www.far.ai/programs/grantmaking to technical researchers.

HEAD OF ENGINEERING (RED TEAM)

FAR.AI is seeking a Head of Engineering (Red Team) to scale one of the world’s most impactful frontier AI red‑teaming programs. This role focuses on building the engineering and execution engine that enables and empowers the red team’s work across testing, 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, provide these stakeholders critical insights and tools, and consistently create the most progress towards safe AI of any red‑teaming group globally. 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 RED-TEAMING AT FAR.AI

FAR.AI’s red team is building toward a simple outcome: materially raising the bar for safety and security of the most widely deployed and 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, resulting in real mitigations, and setting the standard that labs and governments converge on. We also leverage our in‑depth understanding of weaknesses in frontier models to advise frontier developers on mitigations, to guide our own research and grantmaking for improving model security, and to inform the public of key AI risks. We are already one of the leading independent red‑teaming organizations. Our work has helped most Western frontier model developers improve safeguards through pre‑ and post‑deployment testing (e.g., we have directly influenced safeguards at major frontier developers like OpenAI and Anthropic), and are 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

In 2026, we are scaling from a strong team with standout wins into a new level of impact for any AI red team globally:

• Red‑teaming all major frontier model releases (closed and open‑weight) within days/weeks of release;
• Expanding strategic engagements with governments and conducting pre‑deployment testing with most frontier labs;
• Deepening our testing of key risk areas like CBRN, cyber, and agents, and exploring new ones like AI control and alignment;
• Building tools, agents, and insights that raise the global standard for red‑teaming.

ABOUT THE ROLE

As Head of Engineering (Red Team), you will be the senior technical owner of engineering for the FAR.AI http://FAR.AI Red Team, 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. Success looks like vulnerabilities fixed, safeguards strengthened, and global standards shifted – working with leading frontier labs and governments globally to make this happen. Systems your team builds will enable our high‑stakes engagements, accelerate cutting‑edge AI security research, and create the tools/products/services that let us and our partners red‑team the frontier continuously and comprehensively. The current red team will expand in size significantly, and your engineering team will lay the scalable foundation for a relentless and high velocity division to make advanced AI systems safer.

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

• Building a scalable red‑teaming engine: tooling, products, services, evals, agents, and a self‑improving workflow that multiplies output.
• Build and scale internal/external red‑teaming tools and products that improve speed, coverage, and severity of findings.
• Develop agentic red‑teaming systems to automatically and systematically explore the attack space.
• Develop agentic systems to identify new public jailbreaks and other releases, and automatically integrate them into our systems.
• Advance state‑of‑the‑art attacker simulation and output harmfulness evaluation.
• Maintain and evolve internal vulnerability databases, statistical analysis tools, and reporting infrastructure.
• Build systems to empower high‑stakes red‑teaming engagements with frontier AI companies and governments.
• Support public reports, benchmarks, and leaderboards that shape industry norms.
• Contribute to red‑teaming of frontier models (closed‑and open‑weight), improving testing systems both within particular engagements and turning insights from engagements into advances in our overall systems.
• Build agentic workflows that accelerate the red team broadly.
• Initially managing, mentoring, and supporting a growing elite team of engineering / red‑teaming ICs, with extremely high standards for velocity, rigor, judgment, and impact.
• Plan sprints and lead engineering execution.
• Mentor red team ICs in engineering skills, both in direct 1‑1 settings and by building resources for rapid skill growth and knowledge transfer.
• Manage ICs, supporting and amplifying their impact, setting high standards