Staff Security Engineer (Artificial Intelligence)
Confirmed on the employer's own hiring board on Oct 11, 2026. First seen by Alion on Oct 11, 2026.
Join Compass as a Staff Security Engineer specializing in Artificial Intelligence. In this role, you will be the technical authority on securing AI features, working closely with the AI platform and product engineering teams. You will own the AI product security roadmap, drive architectural reviews and threat modeling, build production guardrails, and secure the retrieval layer. You will also harden the AI supply chain, instrument and detect AI-specific abuse, automate security standards, and advise on AI architecture decisions. The ideal candidate will have 7+ years of security engineering experience, with a focus on AI/ML or LLM application security.
Missions
- Assurer la sécurité des fonctionnalités d'intelligence artificielle de Compass, en travaillant en étroite collaboration avec les équipes de développement pour garantir que les normes de sécurité sont respectées.
- Définir la feuille de route de la sécurité des produits d'IA, en élaborant une vision, une stratégie et des normes à long terme pour sécuriser les capacités d'IA de la plateforme Compass.
- Conduire des modélisations de menaces et des examens architecturaux pour les nouvelles fonctionnalités d'IA, en mettant en œuvre des protections en temps réel pour les entrées et sorties des modèles de langage.
Profil recherché
- Automation is your default approach to security, especially when securing complex AI systems at scale- You write production code, strong proficiency in Python or Go, with experience building real integrations and security pipelines, not just prototypes
- You have a deep working understanding of transformer architectures, inference pipelines, RAG, prompt engineering, and the OWASP Top 10 for LLMs
- You communicate well across audiences, translating emerging AI risk into technical roadmaps for engineers and business impact for leadership
- You are proactive about finding and closing gaps in AI/ML workflows through tooling rather than policy
- Strong application and cloud security fundamentals: AWS and/or GCP, Kubernetes, IAM, API security, and DevSecOps practices
- 7+ years in security engineering, with 2+ years focused on AI/ML or LLM application security
- Experience threat modeling complex distributed systems and driving remediation with engineering teams
- Demonstrated experience securing a production AI or ML system end to end, development lifecycle, deployment, and runtime
- Strong strategic communication skills with a proven ability to translate complex technical AI risk into business impact for executive leadership
- Expertise in adversarial ML and LLM risks including prompt injection, model poisoning, data extraction, and unsafe tool use, with hands-on red teaming experience
- Experience with multi-agent autonomous systems or Model Context Protocol (MCP) based architectures
- Familiarity with MITRE ATLAS, NIST AI RMF, or comparable AI threat/risk frameworks
- Background building evaluation and safety-testing harnesses for LLM applications
- Prior work on AI platform security architecture or secure-by-default AI SDKs
- Experience in a regulated or consumer-data-heavy environment where model outputs touch customer-facing decisions