Senior Staff AI/ML Product Security Engineer

Company Description

It all started in sunny San Diego, California in 2004 when a visionary engineer, Fred Luddy, saw the potential to transform how we work. Fast forward to today — ServiceNow stands as a global market leader, bringing innovative AI-enhanced technology to over 8,100 customers, including 85% of the Fortune 500®. Our intelligent cloud-based platform seamlessly connects people, systems, and processes to empower organizations to find smarter, faster, and better ways to work. But this is just the beginning of our journey. Join us as we pursue our purpose to make the world work better for everyone.

Job Description

**Please Note that this role will require a minimum of 2 days in the ServiceNow Offices located in Santa Clara, CA or Kirkland, WA**

The ServiceNow Security Organization (SSO):

The ServiceNow Security Organization (SSO) delivers world-class, innovative security solutions to reduce risk and protect the company and our customers. We enable our customers to migrate their most sensitive data and workloads to the cloud, accelerating our business so that we are the most trusted SaaS provider. We create an environment where our employees are proud to work and can make a positive impact  

The Team:

The Security Research team produces investigative reports that drive a reduction in operational security risk. Paired with a toolkit of code/program and dynamic environmental analysis skills, Security Research provides guidance on primary security controls, best practices, and product enhancement.  

Exploration techniques focus on problems broadly, measuring industry trends and product insecurity across ServiceNow’s cloud environment. A goal of the Research team is to continually drive ServiceNow’s reputation as a leader in cloud security.   

The Role:

As a Senior Staff AI/ML Product Security Engineer, you’ll be responsible for helping secure ServiceNow’s leading edge generative AI product capabilities. You will work with internal AI/ML development teams to perform security reviews of AI Systems throughout the MLOps lifecycle. In this role you’ll be responsible for identifying vulnerabilities, assisting with remediation planning and providing development security support. A key part of this position is understanding, discovering and documenting vulnerabilities in proprietary AI/ML systems which use technologies such as large language models (LLMs). 

What you get to do in this role: 

• Conduct security testing and vulnerability assessments for AI systems, particularly those utilizing large language models (LLMs). 

• Develop and implement security benchmarks and evaluation protocols for LLMs. 

• Identify and mitigate potential security threats and vulnerabilities in AI systems. 

• Collaborate with AI developers to integrate security measures into the development lifecycle. 

• Stay updated on the latest AI security trends and technologies. 

• Provide detailed reports and recommendations based on security evaluations. 
   
   

Qualifications

Experience in leveraging or critically thinking about how to integrate AI into work processes, decision-making, or problem-solving. This may include using AI-powered tools, automating workflows, analyzing AI-driven insights, or exploring AI’s potential impact on the function or industry. 

In order to be successful in this role, we need someone who has:

• An analytical mind for problem solving, abstract thought, and offensive security tactics. 

• Strong interpersonal skills (written and oral communication) and the ability to work collaboratively in a team environment. Ability to articulate complex issues to executives and customers. 

• Post graduate degree and/or related certifications in Machine Learning or Artificial Intelligence. PhD or masters in AI/ML preferred. 

• Strong understanding of probability theory, linear algebra and calculus. 

• 4+ years in a role performing AI/ML Security research and performing security evaluations during model training 

• Knowledge of current academic work in Adversarial attacks of LLMs. 

• In-depth experience with exploiting OWASP LLM Top 10 application vulnerabilities, such as prompt injection and data poisoning 

• Experience training machine learning models including transformer based LLMs. 

• Strong understanding of machine learning frameworks (e.g., TensorFlow, PyTorch) and comprehension of Python code 

• Strong understanding of Natural L