Head of Engineering, Red Team

Job Description: - Build and scale the FAR.AI Red Team engineering organization, systems, tools, products, services, evaluations, and agents

• Develop agentic red-teaming systems to systematically explore attack spaces
• Identify new public jailbreaks and automatically integrate them into red-teaming systems
• Advance attacker simulation and output harmfulness evaluation
• Maintain and evolve vulnerability databases, statistical analysis tools, and reporting infrastructure
• Build systems supporting high-stakes red-teaming engagements with frontier AI companies and governments
• Support public reports, benchmarks, and leaderboards
• Contribute to red-teaming closed- and open-weight frontier models
• Build agentic workflows that accelerate red-team work
• Manage, mentor, and support engineering and red-teaming individual contributors
• Plan sprints and lead engineering execution
• Create scalable processes for high-tempo engagements
• Design hiring pipelines and hire engineering managers and other roles
• Identify engineering bottlenecks and implement solutions
• Partner with technical leadership on engineering systems, methodology, evaluations, and research
• Contribute to red-team technical and product strategy
• Translate technical ideas and findings into real-world 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, including building start-ups (0 → 1) and managing managers
• Experience with coding agents, Python, LLM APIs, local LLM frameworks, evaluation frameworks, LLM agents, cloud infrastructure, and compute clusters
• Experience thriving in rapidly evolving environments
• Demonstrated drive for mission and impact in frontier AI systems
• Ability to communicate technical solutions to technical and non-technical audiences
• Demonstrated relentlessness in achieving ambitious goals
• Experience building or red-teaming frontier LLMs or agentic systems is a plus
• Experience building technical teams and products in an entrepreneurial environment is a plus
• Ability to discover non-obvious, high-severity vulnerabilities in complex systems is a plus
• Experience in adversarial ML or security is a plus
• Prior collaboration with AI labs, security teams, or government safety institutes is a plus
• Published work in AI safety, security, or robustness is a plus
• Some timezone flexibility expected
• Full-time availability (40 hours/week)

Benefits: - Work-related travel expenses paid

• Equipment expenses paid
• Catered lunch and dinner at the office in Berkeley
• Visa sponsorship for the US or Singapore
• Paid work trial