Security Engineer

METR

Security Engineer at METR, a nonprofit R&D organization assessing AI capabilities. Key responsibilities include managing security for frontier AI labs and sensitive information.

Posted 7/29/2026full-timeBerkeley • California • 🇺🇸 United StatesMid-LevelSenior💰 $285,548 - $503,116 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates deep security expertise across systems, networks, cloud, and identity, with a strong focus on offensive security practices such as red teaming and penetration testing. Proficient in building AI systems for threat detection and response, particularly in cloud environments like AWS and Kubernetes.

Highest-signal resume keywords

Deep Security ExpertiseOffensive SecurityAI/LLM EngineeringAWS IAM PoliciesIncident Response

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Red TeamingPenetration TestingThreat HuntingDetection EngineeringIncident ResponseAI Systems DevelopmentCloud SecurityEndpoint ManagementTelemetry PipelinesInfrastructure-as-Code

Tools & Technologies

AWSKubernetesSIEMAI ToolingAutomated Workflows

Industry Keywords

Cloud Platform SecurityIdentity SystemsModel Supply-Chain RisksPrompt InjectionAgent Containment

Tech Stack

Tools & technologies

AWSCloudKubernetes

About the role

Key responsibilities & impact

Security at METR is becoming its own dedicated team, and you would be one of its first hires.
Managing endpoints and securing development environments, cloud platform security, safely sandboxing agents and evaluations.
Run targeted red-team exercises against our own systems and build automated AI red teaming.
Build AI systems that can quickly triage and respond to threats, both from internal agents and external attackers.
Detection engineering, telemetry pipelines, incident response, and hardening across our cloud infrastructure, endpoints, and identity systems.
Securing a unique attack surface: METR's evaluation infrastructure runs frontier AI agents, executing untrusted, model-generated code at scale.
Work closely with researchers to make dangerous-capability experiments safe to run.

Requirements

What you’ll need

Deep security expertise: strong fundamentals across systems, networks, cloud, and identity.
Offensive security: experience acting like an attacker, whether through red teaming, penetration testing, or adversarial research.
AI/LLM engineering: build with AI: agent pipelines, LLM-powered tooling, automated workflows, understand current limitations of those tools.
AWS: deep understanding of IAM policies.
Experience with SIEM/detection pipelines, writing and tuning detections, and threat hunting.
AWS, Kubernetes, and infrastructure-as-code environments.
Incident response: experience leading or working severe incidents, ideally those involving AI agents.
Familiarity with prompt injection, agent containment, model supply-chain risks, or red teaming AI systems themselves.

Benefits

Comp & perks

Catered lunch and dinner daily
in-office gym and shower
Stipend for moving to the Bay Area⁠
Unlimited PTO and 21-week parental leave for new parents
Monthly transit/parking stipend and an 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