AI Security & Testing Engineer

The basics

Tanium is seeking an AI Benchmarking and Safety Testing Specialist to lead the development and execution of comprehensive testing strategies that ensure the robustness and reliability of AI-driven solutions. The AI security Engineer will be an integral part of the R&D organization and collaborate closely with AI, Software, and Security Engineers. This role is crucial in evaluating AI models, identifying potential risks, and implementing safety measures that align with industry standards and regulatory requirements.  

A successful candidate will be a strong technical leader who can bring their industry expertise to drive vision and development cross-functionally across all levels of the organization. Must have a successful track record of doing safety testing and evaluating AI models.  

This is an individual contributor role.    

This is a hybrid position, which will require in person attendance several days each week in one of the following locations: Addison, TX; Bellevue, WA; Durham, NC; Emeryville, CA; or Reston, VA.

 What you'll do

• Develop and execute AI benchmarking and safety testing strategies for various AI models and applications. 
• Design and implement testing protocols to assess the performance, accuracy, and safety of AI solutions.
• Identify potential risks associated with AI technologies and propose mitigation strategies.
• Collaborate with cross-functional teams to integrate safety measures into AI development processes.
• Analyze testing results and provide detailed reports on AI model performance and safety.
• Stay current with industry standards, regulatory requirements, and best practices for AI safety testing.
• Drive continuous improvement in AI safety testing methodologies and tools. 

We're looking for someone with

• Education
  • Bachelor's degree in computer science, Engineering, or related field. 
• Experience
  • 8+ years of relevant work experience.
  • Expertise with common security testing methodologies.
  • Experience with regulatory compliance and industry standards for AI safety.
  • Familiarity with AI development frameworks and tools.
  • Strong understanding of AI and machine learning algorithms and their associated risks.
  • Experience with LLMs, AI Agents, and Natural Language Processing (NLP) techniques, with a focus on safety testing and benchmarking.
• Other 
  • Strong analytical and problem-solving skills. Excellent communication and collaboration abilities.
  • Detailed oriented individual with a deep drive to research the security of bleeding edge technology. 

About Tanium 

Tanium delivers the industry's only true real-time cloud-based endpoint management and security offering. Its platform is real-time, seamless, and autonomous, allowing security-conscious organizations to break down silos between IT and Security operations that results in reduced complexity, cost, and risk. Securing more than 32M endpoints around the world, Tanium's customers include Fortune 100 organizations, top US retailers, top US commercial banks, and branches of the U.S. Military. It also partners with the world's biggest technology companies, system integrators, and managed service providers to help customers realize the full potential of their IT investments. Tanium has been named to the Forbes Cloud 100 list for nine consecutive years and ranks on the Fortune 100 Best Companies to Work For. For more information on The Power of Certainty™, visit www.tanium.com and follow us on LinkedIn and X. 

On a mission. Together. 

At Tanium, we are stewards of a culture that emphasizes the importance of collaboration, respect, and diversity. In our pursuit of revolutionizing the way some of the largest enterprises and governments in the world solve their most difficult IT challenges, we are strengthened by our unique perspectives and by our collective actions.   

We are an organization with stakeholders