About Xerox Holdings Corporation

For more than 100 years, Xerox has continually redefined the workplace experience. Harnessing our leadership position in office and production print technology, we've expanded into software and services to sustainably power the hybrid workplace of today and tomorrow. Today, Xerox is continuing its legacy of innovation to deliver client-centric and digitally-driven technology solutions and meet the needs of today's global, distributed workforce. From the office to industrial environments, our differentiated business and technology offerings and financial services are essential workplace technology solutions that drive success for our clients. At Xerox, we make work, work. Learn more about us at www.xerox.com.

Position Overview

We are seeking an experienced and highly motivated senior AI Security Engineer with deep expertise in securing AI/ML technologies, particularly in the context of leading cloud platforms such as AWS and MS Azure. The ideal candidate will possess a strong understanding of security best practices for AI/ML workloads, including the application of AWS Bedrock best practices, and will play a pivotal role in designing, implementing, and maintaining robust security solutions for our AI-powered solutions in Cloud environments.

Primary Responsibilities:

Familiarity with secure prompt engineering and LLM guardrails along with knowledge of responsible AI principles and robustness evaluation frameworks.
Knowledge of Adversarial Attack Techniques - Evasion attacks, Poisoning attacks, Model inversion & extraction, Prompt injection attacks, jailbreak testing for LLMs and generative AI systems.
Conduct security risk assessments, threat modelling, and vulnerability management for AI/ML workloads in the cloud.
Design, implement, and manage cloud security architectures for AI/ML services and applications across AWS (including Bedrock), and Azure Cloud platforms.
Develop and enforce security best practices, policies and controls for AI/ML technologies, data security, models, endpoints, APIs and MCP servers.
Collaborate with Data Scientists, DevOps, and Engineering teams to integrate security throughout the AI/ML lifecycle.
Monitor and respond to security incidents involving AI/ML resources and infrastructure, ensuring rapid mitigation and remediation.
Champion the adoption of AWS Bedrock security best practices, including data encryption, access control, and compliance automation for generative AI services and Agentic AI implementations.
Stay abreast of emerging threats, vulnerabilities, and regulatory requirements relating to AI/ML security.

Required Qualifications:

Bachelor's degree or equivalent practical experience.
Minimum 10 years of experience with security assessments or security design reviews or threat modeling.
Minimum 4 years of experience in cloud security, security engineering, computer and network security
Minimum 2 years of experience focused on AI/ML technologies in cloud environments.
Ability to quantify risks to AI solutions based on standard mechanisms like AI RMF, OWASP ML Security top 10, MITRE ATLAS etc.
Hands-on experience with Azure AI and AWS (including AWS Bedrock) Platform.
Strong understanding of AI/ML security risks, including data privacy, model security, and AI-specific threat vectors.
Proficiency in designing and implementing security controls for cloud-native AI/ML services (e.g., IAM, KMS, VPC, encryption, network segmentation).
Excellent analytical, problem-solving, and communication skills.

Preferred Skills:

Certifications such as AWS Certified Security – Specialty, or Certified Information Systems Security Professional (CISSP).
Knowledge of secure AI/ML model deployment strategies, adversarial robustness, and responsible AI practices.
Experience with infrastructure as code (Iac) tools (e.g., Terraform, CloudFormation) and security automation.
Experience working in agile, multicultural, and cross-functional teams.

Soft Skills Required:

Strong interpersonal skills as well as excellent written and verbal communication skills
Uncompromising personal and professional integrity and ethics.
Clear articulation of complex technical concepts to both technical and non-technical stakeholders.
Creative and analytical thinking to navigate challenges and develop innovative solutions.
Evaluating situations logically to make informed decisions and anticipate potential risks.
Prioritizing tasks and managing deadlines efficiently while managing stakeholders.

Staff Security Engineer - Cloud & AI Security