Tenable, Inc.
AI Information Security Engineer
About this role
Tenable seeks an AI Security Engineer to design and implement security controls across AI/ML systems, from model internals inspection to enterprise deployment. You'll conduct safety research, threat modeling, and build guardrails for LLMs while collaborating with engineering teams to embed security throughout the AI lifecycle.
What you'll do
- Design end-to-end security controls for AI/ML systems and conduct safety research by inspecting model internals
- Perform threat modeling and security assessments for AI systems, identifying risks like data poisoning, model evasion, and adversarial attacks
- Develop security guardrails and boundary mechanisms for LLMs, SLMs, and open-source models
- Build reference architectures for secure AI deployment patterns including agentic workflows
- Collaborate with engineering and product teams to integrate security into AI development and CI/CD pipelines
- Research emerging AI vulnerabilities and create security guidance and training for internal teams
What they're looking for
- AI/ML security and adversarial machine learning
- Python and/or Go programming
- Model interpretability tools (TransformerLens, NNsight, Captum, LIT)
- PyTorch, Hugging Face Transformers, TensorFlow
- Cloud security (AWS, Azure, GCP)
- Threat modeling and SSDLC/DevSecOps practices
- Application security architecture and microservices
- Data security principles and encryption
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Tenable, Inc.
Tenable provides cybersecurity solutions including vulnerability analysis and threat detection products. The company is hiring Technical Support Engineers to assist customers with these platforms, Pre-Sales Engineers to drive enterprise sales, and a Salesforce Developer to support internal business technology operations.
- Website
- tenable.com
Likely interview questions
- Describe your hands-on experience building and securing AI systems—what specific threats or vulnerabilities have you encountered?
- Walk us through your approach to inspecting model internals; which interpretability tools have you used and what did you discover?