Security Engineer
About The Position
METR is seeking a Security Engineer to join its newly formed dedicated security team. This role is crucial for maintaining the trust of frontier AI labs, governments, and the public, especially concerning sensitive model access and confidential information. As AI risks escalate and the value of confidential AI information grows, the organization anticipates increased pressure. Security at METR encompasses managing endpoints, securing development environments, cloud platform security, safely sandboxing agents and evaluations, VPN and VPC networking, application code reviews, account provisioning, access control, and promoting best practices across all workflows.
Requirements
- Deep security expertise with strong fundamentals across systems, networks, cloud, and identity.
- Experience acting as an attacker through red teaming, penetration testing, or adversarial research.
- Experience building with AI, including agent pipelines, LLM-powered tooling, and automated workflows, with an understanding of their limitations.
- Proficiency in AWS, with a deep understanding of IAM policies.
Nice To Haves
- Experience with SIEM/detection pipelines, writing and tuning detections, and threat hunting.
- Experience with cloud and container security, including AWS (especially non-trivial IAM), Kubernetes, and infrastructure-as-code environments.
- Experience leading or working on severe incidents, ideally involving AI agents.
- Familiarity with AI security research topics such as prompt injection, agent containment, model supply-chain risks, or red teaming AI systems.
- Experience with technologies including AWS (cloud-native software platforms, EKS, Lambda, ECS, IAM, SQS, CloudWatch, SecurityHub & GuardDuty), PostgreSQL (RLS, serverless Aurora), Pulumi (IaC), DataDog (SIEM), Okta (IdP), Google Workspace (IdP), Tailscale (networking), and CrowdStrike Falcon (endpoint security).
Responsibilities
- Run targeted red-team exercises against internal systems.
- Build automated AI red teaming capabilities.
- Develop AI systems for rapid triage and response to threats from internal agents and external attackers.
- Engage in detection engineering, manage telemetry pipelines, and handle incident response.
- Harden cloud infrastructure, endpoints, and identity systems.
- Secure a unique attack surface involving frontier AI agents, including early checkpoints of unreleased models, executing untrusted code at scale.
- Collaborate with researchers to ensure the safety of dangerous-capability experiments, addressing challenges like extreme reward hacking and evaluation awareness.
- Investigate and respond to misalignment incidents involving AI agents breaking out of sandboxes, attacking infrastructure, or manipulating systems.
Benefits
- Catered lunch and dinner daily
- In-office gym and shower
- Stipend for moving to the Bay Area
- Unlimited PTO
- 21-week parental leave for new parents
- Monthly transit/parking stipend
- Annual Uber budget
- Professional development benefit for training, courses, conferences, and AI safety education
- Mental health benefit for therapy, medication, and other mental health expenses
- Wellness benefit for gym memberships and other wellness expenses
- Work equipment benefit for home office and workstation equipment expenses
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
