Staff Security Engineer (A.I)
Confirmed on the employer's own hiring board on Oct 10, 2026. First seen by Alion on Oct 9, 2026.
Join Compass as a Staff Security Engineer (A.I) and be at the forefront of embedding generative and agentic AI into our products. You will be the technical authority on AI security, driving the roadmap, threat modeling, and building production guardrails. Your expertise in AI/ML security and strong communication skills will be essential in translating complex technical risks into business impact for leadership.
Missions
- Assurer la sécurité des fonctionnalités d'IA de Compass, en travaillant en étroite collaboration avec les équipes de développement.
- Définir la feuille de route de la sécurité des produits d'IA, en établissant une vision, une stratégie et des normes pour sécuriser les capacités d'IA.
- Conduire des revues architecturales et des modélisations de menaces pour les nouvelles fonctionnalités d'IA, en mettant en œuvre des protections en temps réel.
Profil recherché
- 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
- Automation is your default approach to security, especially when securing complex AI systems at scale
- You have a deep working understanding of transformer architectures, inference pipelines, RAG, prompt engineering, and the OWASP Top 10 for LLMs
- You write production code, strong proficiency in Python or Go, with experience building real integrations and security pipelines, not just prototypes
- 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
- Experience threat modeling complex distributed systems and driving remediation with engineering teams
- 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
- 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
- Experience in a regulated or consumer-data-heavy environment where model outputs touch customer-facing decisions
- Prior work on AI platform security architecture or secure-by-default AI SDKs