Engineering Manager, Red Team

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

📋 Description

• Act as the senior technical leader for engineering within FAR.AI’s Red Team.

• Design and expand a red-teaming engine that includes tooling, products, services, evaluations, agents, and self-enhancing workflows.

• Create and enhance internal and external red-teaming tools and products to boost speed, coverage, and severity of findings.

• Develop agentic systems to methodically investigate attack surfaces.

• Create agentic systems to discover new public jailbreaks and releases, integrating them into internal frameworks.

• Enhance attacker simulation and assess harmfulness outputs.

• Maintain and upgrade vulnerability databases, statistical analysis tools, and reporting infrastructure.

• Construct systems that support high-stakes red-teaming operations with leading AI firms and governmental bodies.

• Assist in public reports, benchmarks, and leaderboards that shape industry standards.

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

• Develop broadly enhancing agentic workflows for the red team.

• Manage, mentor, and provide support to a growing team of red-teaming individual contributors.

• Organize sprints and oversee engineering execution.

• Guide red team individual contributors through direct one-on-one support and reusable growth resources.

• Establish standards and priorities while creating pathways for rapid team development.

• Implement processes for high-tempo engagements without compromising quality.

• Design and oversee hiring pipelines for the engineering team.

• Contribute to the red-team's technical and product strategy.

• Collaborate with the division to translate technical concepts and findings into real-world applications.

• Report to Kellin Pelrine with a dotted line to Edward Yee.

⛳️ Requirements

• Proven experience in software engineering, AI, or related computer engineering fields, such as cybersecurity or MLOps.

• Strong history of managing, developing, and leading technical teams.

• Proficiency in coding agents like Claude Code, Codex, or Cursor.

• Experience with Python programming.

• Familiarity with LLM APIs such as OpenAI, Anthropic, or Google.

• Experience with local LLM frameworks like vLLM.

• Knowledge of evaluation frameworks such as Inspect.

• Experience with LLM agents like OpenClaw.

• Competence in cloud infrastructure such as GCP.

• Experience with compute clusters like Kubernetes or Slurm.

• Ability to thrive in rapidly changing environments.

• A strong drive for mission-focused work and impact on frontier AI systems.

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

• Proven persistence in reaching ambitious objectives.

• Leadership experience is essential.

• Willingness to engage in hands-on coding and engineering, particularly in the first six months.

• Openness to participate in team building and hiring activities.

• Flexibility in time zones is required.

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

• Experience in building or red-teaming frontier LLMs or agentic systems is advantageous but not mandatory.

• Experience in developing technical teams and products in an entrepreneurial setting is a plus, but not required.

• Experience in uncovering non-obvious, high-severity vulnerabilities in complex systems is beneficial, but not required.

• Hands-on experience in adversarial ML or security is a plus, but not required.

• Prior collaboration with AI labs, security teams, or government safety organizations is advantageous, but not required.

• Published work in AI safety, security, or robustness is a plus, but not required.

🏝️ Benefits

• Additional compensation may be available for exceptional candidates.

• Coverage for work-related travel expenses.

• Coverage for work-related equipment expenses.

• Catered lunch and dinner provided at FAR.AI offices in Berkeley.

• Visa sponsorship available for the USA or Singapore.