We sent a six-digit code to . Enter it below — or use the link in the same email.
Or click the link in the same email — either works.
Enter the email address on your account and we'll send you a link to set a new password.
Remembered it? Sign In
We are a nonprofit research organization that develops scientific methods to assess AI capabilities, risks, and mitigations, with a specific focus on threats related to AI R&D automation and misalignment.
We believe it is robustly good for policymakers and civil society to have a clear understanding of risks from AI systems, and we are extremely excited to build a team of ambitious, excellent people to tackle one of the most important challenges of our time.
METR’s mission of enabling transparency and coordination about the risks of frontier AI requires a high degree of trust from frontier AI labs, governments, and the public. As misalignment incidents become more extreme and confidential information about models and frontier AI labs becomes more valuable, we expect to be under increasingly intense pressure from external actors and internal agents.
METR is looking to expand the security expertise on our platform team. This would span application security in our evaluation platform, sandboxing agents and evaluations, cloud platform security, networking, access control for both people and agents, and securing our development environments and workflows. This role will have a large engineering component: expect to write and review code, fix vulnerabilities, and design and develop secure systems.
Securing a unique attack surface. METR's evaluation infrastructure runs frontier AI agents, including early checkpoints of unreleased models, executing untrusted, model-generated code at scale on multi-day tasks. You will design and build the isolation, networking, and permission boundaries that contain evaluated agents.
Remediation and hardening. You will find, triage, and fix vulnerabilities across our cloud infrastructure and access control systems.
Fixing known vulnerabilities in our codebase. This includes code reviews and resolving known vulnerabilities in our backlog.
Identity and access as a system. You will design and implement IAM policies, least-privilege access, and automated provisioning and access review for both people and agents.
Securing agentic systems. You will design and implement systems to monitor and control agents, making sure they can operate securely and with appropriate permissions and guardrails.
7+ years of experience working in security engineering, software development, or an adjacent field.
Production software engineering. You have experience building and operating backend or infrastructure in practice.
Cloud and container security. You have deep familiarity with AWS (especially non-trivial IAM), Kubernetes, and infrastructure-as-code environments.
Vulnerability remediation. You have found and fixed security flaws in large production systems and can prioritize a remediation backlog.
Security fundamentals. Strong security knowledge across systems, networks, cloud, and identity, and a track record of applying it to real systems. Experienced in designing secure software and cloud architectures.
Code review. Reviewing and giving constructive security feedback on PRs, including from the FOSS community.
Detection engineering at scale: Experience with detection pipelines (DataDog SIEM, AWS SecurityHub), writing and tuning detections, and threat hunting.
AI/LLM engineering: You build with AI: agent pipelines, LLM-powered tooling, automated workflows, and understand current limitations of those tools.
AI security research: Familiarity with agent control, hardware security, or red teaming AI systems themselves.
Ideally you have experience with a portion of these technologies:
AWS: cloud-native software platforms
EKS
Lambda
ECS
IAM (in-depth)
CloudWatch
SecurityHub & GuardDuty
PostgreSQL: RLS, serverless Aurora
Pulumi: IaC
DataDog: SIEM
Okta: IdP
Google Workspace: IdP
Tailscale: networking
CrowdStrike Falcon: endpoint security
Here is what this employer asked for. Sign in and we will fill in your half.
METR is a research nonprofit that evaluates frontier AI models to help companies and wider society understand AI capabilities and what risks they pose.
202K – 326K
Our estimate — this employer did not publish a salaryOur estimate, not the employer’s. Worked out from the middle half of 40 comparable roles on Neural Jobs that did publish a salary, in the same field, country and experience band. The real figure for this job may be different.
Search by role, company, or anything a posting mentions.
