Engineering Manager (Red Team)

FAR.AI•,

6d•$170,000 - $250,000•Remote

About The Position

FAR.AI is a non-profit AI research institute focused on AI safety and beneficial AI. The Red Team at FAR.AI is dedicated to significantly improving the safety and security of advanced AI systems. This role involves leading the engineering efforts for the Red Team, building systems and tools to test critical safeguards of next-generation AI models. The goal is to identify vulnerabilities, strengthen safeguards, and influence global standards by working with leading AI companies and governments. The position requires a blend of hands-on engineering and team building, with a focus on scaling the team's capabilities and impact.

Requirements

Strong track record in software engineering, AI, or another computer engineering discipline (e.g. cybersecurity, MLOps).
Strong track record of managing, growing, and leading technical teams.
Experience with parts of the tech stack commonly used, such as coding agents (e.g., Claude Code, Codex, Cursor), Python, LLM APIs (e.g. OpenAI, Anthropic, Google), local LLM frameworks (e.g., vLLM), evaluation frameworks (e.g., Inspect), LLM agents (e.g., OpenClaw), cloud infrastructure (e.g. GCP), compute clusters (e.g. Kubernetes, Slurm).
Thrived in rapidly evolving environments.
Demonstrated drive for mission/impact and desire to create a real impact on frontier AI systems.
Can effectively communicate technical solutions to both technical and non-technical audiences.
Demonstrated relentlessness in achieving ambitious goals.

Nice To Haves

Experience building or red-teaming frontier LLMs or agentic systems.
Experience building technical teams and products in an entrepreneurial environment.
Demonstrated ability to discover non-obvious, high-severity vulnerabilities in complex systems.
Other hands-on experience in closely related areas like adversarial ML or security.
Prior collaboration with AI labs, security teams, or government safety institutes.
Published work in AI safety, security, or robustness.

Responsibilities

Build and scale internal/external red-teaming tools and products to 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.
Support public reports, benchmarks, and leaderboards that shape industry norms.
Contribute to the red-teaming of frontier models (closed- and open-weight), improving testing systems and turning insights into overall system advances.
Build agentic workflows that accelerate the red team broadly.
Manage, mentor, and support a growing elite team of 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 and prioritization week-to-week, and creating the environment and paths for rapid growth.
Create processes that scale high-tempo engagements without sacrificing quality.
Design and be hiring manager for pipelines to scale the engineering team, in partnership with others on the red team and the org’s recruiting team.
Contribute to the overall technical and product strategy of the red team.
Partner closely with the rest of the division to translate technical ideas and findings into real-world impact.