Manager - AI Safety and Trust Architect

Location:

Anywhere in Country

At EY, we’re all in to shape your future with confidence. We’ll help you succeed in a globally connected powerhouse of diverse teams and take your career wherever you want it to go. Join EY and help build a better working world.

Manager – AI Safety and Trust Architect

We’re hiring an experienced AI Safety Architect that is an expert in modern AI explainability, formal methods, and complex system behaviors. Knowledge of causal methods, process calculus, mechanistic concept activation, and formal methods used in the development of AI behavioral safety is required. The successful candidate should have experience in the emerging area of AI behavioral safety, thrive in fast‑paced environments, and be passionate about enabling scalable AI solutions.

• Develop effective AI Safety designs for implementation into trust and assurance frameworks for enterprise AI agent‑based applications and internal EY platforms.
• Support selection and application of formal methods to ensure safety.
• Develop best practices for AI safety design patterns in AI‑native applications.
• Design cryptographically secure methods of verification and evaluation assessments based on explainable behaviors.
• Assess new proposed projects to ensure they are leveraging best safety practices, architecture design, and implementation.
• Collaborate with other architectural experts in AI, Data, and Infrastructure to ensure balanced and practical outcomes.
• Support strategic business development activities for emerging technology.

• Strong analytical and troubleshooting skills.
• Ability to lead AI safety architectural product functions and mentor junior engineers.
• Comfortable working across cross‑functional teams and managing competing priorities.
• Build and manage strong internal and external partnerships by fostering trust, empathy, and mutual value.
• Leverage emotional agility and hybrid collaboration to navigate diverse stakeholder needs and drive long‑term engagement.
• Use critical thinking and creative reasoning to address complex problems and exceed expectations.
• Align cross‑functional teams around shared goals, ensuring accountability and progress; use emotional intelligence and hybrid collaboration to motivate others and deliver high‑impact results.

• 5+ years of experience in AI engineering, verified systems, and architecture.
• Masters or PhD in Computer Science, Electrical Engineering, or Mathematics.
• Understanding of security and safety in AI explainability, safety methods, etc.
• Experience with operational and behavioral AI safety techniques and implementations.
• Understanding of threat models of AI adversarial attacks.
• Familiarity with trust frameworks and formal methods of verification.
• Expertise in the assessment of best practices for agile development processes.
• Expertise in the development and adoption of safety‑first best practices.
• Familiarity with causal and other techniques.

• Experience with large‑scale cross‑functional software development projects.
• Excellent communication and leadership abilities.

At EY, we’ll develop you with future‑focused skills and equip you with world‑class experiences. We’ll empower you in a flexible environment, and fuel you and your extraordinary talents in a diverse and inclusive culture of globally connected teams.

• We offer a comprehensive compensation and benefits package where you’ll be rewarded based on your performance and recognized for the value you bring to the business. The base salary range for this job in all geographic locations in the US is $125,500 to $230,200. The base salary range for New York City Metro Area, Washington State and California (excluding Sacramento) is $150,700 to $261,600.
  
  Individual salaries within those ranges are determined through a wide variety of factors including but not limited to education, experience, knowledge, skills and geography. In addition, our Total Rewards package includes medical and dental coverage, pension and 401(k) plans, and a wide range of paid time off options.
• Join us in our team‑led and leader‑enabled hybrid model.…