Senior Director AI Security 664

Position Overview

• Location Type: Remote
• Job Type: Full-Time
• Salary: $245K - $400K

Protegrity is a global leader in data security, innovating with AI and quantum-resistant cryptography to protect data across various environments. We aim to make data valuable, usable, trusted, and safe. This role offers the chance to work at the forefront of innovation and collaboration, impacting the data security industry.

Position

Senior Director, AI Security

Role Summary

Join Protegrity's GenAI Security Team to shape the future of GenAI security. This role involves hands-on work and leadership in developing next-generation AI governance, safety, security, and privacy frameworks. You will leverage expertise in AI/ML, generative AI, unstructured data, and LLMs, collaborating with a diverse team to set industry standards and drive business innovation. This is a unique opportunity to lead groundbreaking projects while remaining technically involved.

Responsibilities

• Lead research on securing Generative AI, NLP, and LLMs for unstructured data processing, focusing on safety guardrails and compliance.
• Conduct advanced AI/ML security research and experimentation to develop novel algorithms and scalable solutions for secure GenAI systems.
• Develop and optimize models, tools, and methodologies to detect and mitigate risks in LLMs, including bias, toxicity, and hallucination.
• Architect and deploy robust frameworks for AI system governance, ensuring compliance with industry standards and regulations.
• Build end-to-end pipelines for training, evaluation, and deployment of GenAI systems with a focus on operational excellence.
• Incorporate state-of-the-art safety measures, including adversarial testing, bias mitigation, and secure access controls.
• Act as an evangelist by publishing white papers, contributing to industry forums, and advising stakeholders on GenAI trends.
• Lead collaborations with researchers, engineers, and product teams to integrate AI models into enterprise-grade product solutions.
• Provide thought leadership in AI governance and security, mentoring cross-functional teams and stakeholders.
• Partner with legal, compliance, and ethics teams to ensure adherence to regulatory standards and ethical AI practices.

Qualifications

• Experience: 12-15 years in AI/ML, security, governance, and safety, with at least 2 years specializing in GenAI and LLMs.
• AI/LLM Expertise:
  • Building and optimizing AI/LLM-based data classification systems.
  • Utilizing AI/LLM-based techniques for trust, risk, safety, and security guardrails of GenAI systems.
  • Developing secure and privacy-preserving AI solutions.
• Tools & Technologies: Familiarity with tools like Lang Chain, Hugging Face, OpenAI APIs, etc.
• AI Lifecycle Management: In-depth understanding of bias mitigation, explainability, and robustness testing.
• Programming Skills: Advanced proficiency in Python; knowledge of RUST, Java, and Go is a plus.