Head of Engineering, Red Team

This is a fully remote position, open to applicants anywhere in the world.

📋 Description

• Establish and expand the FAR.AI Red Team engineering team, including systems, tools, products, services, evaluations, and agents.

• Create agentic red-teaming systems to systematically investigate attack landscapes.

• Discover new public jailbreaks and seamlessly incorporate them into red-teaming systems.

• Enhance attacker simulation and assess the potential harmfulness of outputs.

• Maintain and improve databases of vulnerabilities, statistical analysis tools, and reporting infrastructure.

• Develop systems that support high-stakes red-teaming operations with cutting-edge AI companies and government entities.

• Assist with public reports, benchmarks, and leaderboards.

• Contribute to red-teaming efforts on both closed- and open-weight frontier models.

• Create agentic workflows that expedite red-team activities.

• Oversee, mentor, and provide support to individual contributors in engineering and red-teaming.

• Organize sprints and guide engineering execution.

• Establish scalable processes for high-tempo engagements.

• Design hiring pipelines and recruit engineering managers and other positions.

• Identify engineering bottlenecks and implement effective solutions.

• Collaborate with technical leadership on engineering systems, methodologies, evaluations, and research.

• Contribute to the technical and product strategy of red-teaming initiatives.

• Transform technical concepts and discoveries into tangible real-world impact.

⛳️ Requirements

• Proven experience in software engineering, AI, or a related computer engineering field (such as cybersecurity or MLOps).

• Demonstrated history of managing, developing, and leading technical teams, including building startups (0 → 1) and supervising managers.

• Proficiency in coding agents, Python, LLM APIs, local LLM frameworks, evaluation frameworks, LLM agents, cloud infrastructure, and compute clusters.

• Experience thriving in fast-paced and evolving environments.

• A strong commitment to mission-driven work and impact in frontier AI systems.

• Capability to articulate technical solutions to both technical and non-technical audiences.

• Proven determination in reaching ambitious objectives.

• Experience in building or red-teaming frontier LLMs or agentic systems is advantageous.

• Background in developing technical teams and products within an entrepreneurial environment is a plus.

• Ability to identify non-obvious, high-severity vulnerabilities in complex systems is a plus.

• Background in adversarial ML or security is a plus.

• Previous collaboration with AI labs, security teams, or government safety organizations is a plus.

• Published research in AI safety, security, or robustness is a plus.

• Some flexibility in time zones is expected.

• Availability for full-time work (40 hours per week).

🏝️ Benefits

• Coverage for work-related travel expenses.

• Reimbursement for equipment expenses.

• Catered lunch and dinner provided at the office in Berkeley.

• Visa sponsorship available for the US or Singapore.

• Paid work trial offered.