Senior Security Engineer AI Safety
Posted Updated 2
views
Description
You will secure AI platforms and autonomous workflows by developing AI risk frameworks, protecting model artifacts, deploying LLM guardrails, and embedding controls across the ML lifecycle. You will lead AI-security incident response, automate threat mitigation, and support compliance and AI safety implementation.
Responsibilities
- Conduct AI and machine learning threat modeling
- Create risk management frameworks for AI systems
- Protect model weights, code, and training data
- Design LLM guardrails, sandboxing, and monitoring controls
- Implement security controls across the machine learning lifecycle
- Lead technical response to AI security incidents
- Automate threat hunting and mitigation
- Automate compliance monitoring and metrics
- Implement AI safety standards with legal and compliance partners
Requirements
- Understanding of deep learning frameworks, cloud training or inference infrastructure, and LLM ecosystems
- Familiarity with prompt injection, model inversion, data poisoning, OWASP Top 10 for LLMs, or MITRE ATLAS
- Experience securing agentic frameworks including ADK and MCP
- Experience with agent-to-agent identity and access controls
- Cloud platform and container security proficiency, preferably GCP
- Ability to write production-grade Python or equivalent automation code
- Risk assessment and mitigation experience
- Ability to communicate machine learning risks to leadership
Skills
Sign in to read and join the discussion.