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 grant-making 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. Our work is also assisting 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.
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;
This is a force-multiplier role. You will report to Edward Yee (Head of Growth & Strategy, who also leads the red-team), dotted line to Kellin Pelrine (co-leading and technical lead for the red-team). You will work alongside our red-teamers, researchers, and the rest of the team to turn a fast-growing team and portfolio of engagements into a reliable, high-velocity delivery team.
The red-team has ambitious goals and is evolving rapidly, and we expect this role to evolve to fit the priorities of the team. Our team is scaling from 2 to 15+ this year, with candidate profiles that require active sourcing and careful shepherding in order to hire the very best talent. Our engagement portfolio across frontier labs and governments is already complex and will grow further. You will be moderately technical — comfortable enough with red-teaming substance to read a report, engage credibly with technical colleagues, do technical writing/reviews, and understand what we are hiring for. You do not need to jailbreak models yourself, but you should be able to meet our red-teamers on their terms. Our best guess for the 2026 shape:
•
Engagement delivery (~35%). Own the delivery of our largest multi-party engagement. Take delivery ownership of other engagements as they come in such as frontier-model red teaming engagements and government RFPs. Run the request for proposals (RFP) and opportunity pipeline — tracking live opportunities, scoping new engagements, drafting proposals, and supporting contract negotiations. Program-manage new initiatives as they land, such as grant- making.
•
Red-team recruiting (~30%). Own the red-team scaling roadmap, partnering closely with the lead recruiter around building a world-class hiring pipeline that anchors our scaling plans. Drive red-team hiring initiatives, serving as a thought partner on sourcing strategy, candidate calibration, hiring bar, and process improvements. Collaborate with the red-team leadership to source, sell, and close top global talent. This complements our org-wide technical recruiting function rather than replacing it.
•
Misc (~35%). The red-team’s needs will shift through the year. Likely stretch work includes analysis (e.g., identifying bottlenecks in our throughput, mapping the ecosystem of competitor and partner organizations), technical writing, event organizing (convenings, workshops), support on policy and government-facing work, grant applications, and ad-hoc projects that need an owner. We will allocate this together based on what the team needs most, where you have comparative advantage, and where you want to grow.
We expect the balance to shift as the team grows.