Senior AI Security Engineer — Secure AI Platform

Compass, Inc.; New York (NY); On-site; USD 210,000 - 234,000; Full time

Benefits offered by this job

Bonuses & stock options

Medical, dental, vision insurance

401(k) plan

Job summary

Compass, Inc. is seeking a security engineer to own the AI product security roadmap, enforce threat modeling, and build real-time protections for AI features.

You will work with the AI platform and product teams to ensure secure, compliant, and scalable AI capabilities across the Compass platform. The role requires deep expertise in AI/LLM security, cloud security, and secure-by-default practices, with a focus on preventing prompt injection, data leakage, and unsafe tool use in production

Qualifications

• 7+ years in security engineering with 2+ years focused on AI/ML or LLM application security.
• Demonstrated experience securing a production AI or ML system end to end, development lifecycle, deployment, and runtime.
• Expertise in adversarial ML and LLM risks including prompt injection, model poisoning, data extraction, and unsafe tool use, with hands-on red teaming experience.
• Strong application and cloud security fundamentals: AWS and/or GCP, Kubernetes, IAM, API security, and DevSecOps practices.
• Experience threat modeling complex distributed systems and driving remediation with engineering teams.
• Strong strategic communication skills with a proven ability to translate complex technical AI risk into business impact for executive leadership.

Responsibilities

• Own the AI product security roadmap and set multi-year visions, standards, and governance.
• Conduct threat modeling for new AI features, RAG pipelines, multi-agent workflows, and automated decisioning before release.
• Build and automate real-time protections for LLM inputs/outputs including injection defense and data exfiltration checks.
• Define blast-radius controls for autonomous agents with permissions, human-in-the-loop checks, and audit trails.
• Secure the retrieval layer with strict data access controls and tenancy boundaries across RAG/vector stores.
• Harden the AI supply chain by evaluating third-party models, providers, and data use terms.
• Instrument monitoring: create detections for AI abuse, anomalous tool invocation, and retrieval anomalies.
• Deliver reusable security libraries, CI/CD checks, and evaluation harnesses to make secure AI the default.
• Advise leadership on AI architecture risk and translate findings into actionable roadmaps.

Skills

AI/LLM security

Threat modeling

Python

Go

Adversarial ML

Cloud security

Kubernetes

DevSecOps

Communication

Security engineering

Tools

AWS

GCP

Kubernetes

IAM

Job description

Compass, Inc. is seeking a security engineer to own the AI product security roadmap, enforce threat modeling, and build real-time protections for AI features.

You will work with the AI platform and product teams to ensure secure, compliant, and scalable AI capabilities across the Compass platform. The role requires deep expertise in AI/LLM security, cloud security, and secure-by-default practices, with a focus on preventing prompt injection, data leakage, and unsafe tool use in production