Security Engineer

AI71 is an applied research team dedicated to creating helpful and responsible AI agents for knowledge workers. Working closely with industry partners, our cross-functional teams of AI experts build products grounded in the cutting-edge research of the Technology Innovation Institute (TII). Our mission is to advance AI applications, particularly those utilizing Large Language Models (LLMs), enabling businesses to unlock the full potential of AI.

We are looking for a talented Security Engineer to join our team, responsible for ensuring that our AI-driven solutions are secure, compliant, and resilient from the ground up.

As a Security Engineer, you will play a crucial role in securing the infrastructure, systems, and data involved in our LLM-powered solutions. Collaborating closely with product teams, DevOps, and AI experts, you will design, implement, and maintain security measures to protect our AI models, client data, and AI solutions. You will also ensure compliance with security best practices and regulatory standards while mitigating emerging threats in the rapidly evolving AI landscape.

Key Responsibilities:

• Security Architecture & Design: Collaborate with engineering and AI teams to design secure architectures for LLM-based solutions.
• Threat Detection & Response: Monitor, detect, and respond to security threats across AI systems, leading investigations into potential security incidents.
• Vulnerability Management: Conduct regular vulnerability assessments, penetration testing, and security audits on AI systems and infrastructure.
• Data Privacy & Compliance: Ensure compliance with data protection regulations such as GDPR, HIPAA, or CCPA.
• Cloud Security: Oversee the security of cloud-based AI infrastructure (AWS, GCP, Azure).
• Security Automation: Automate security monitoring, incident response, and patching processes.
• Model Security: Ensure the secure deployment of LLM models and protection against model manipulation.
• Collaboration & Training: Work with internal teams to integrate security best practices into the AI development lifecycle.

Qualifications:

• Bachelor's or Master’s degree in Computer Science, Cybersecurity, or a related field.
• 5+ years of experience in a security engineering role focusing on infrastructure, application, and cloud security.
• Experience securing machine learning models, particularly large-scale LLMs.
• Strong knowledge of cloud platforms (AWS, GCP, Azure) and security best practices.
• Familiarity with AI/ML-specific security challenges.
• Proficiency in scripting languages (e.g., Python, Bash) for automating security tasks.

Preferred Qualifications:

• Experience with securing AI/ML applications involving NLP or LLM technologies.
• Certifications in cybersecurity (e.g., CISSP, AWS Certified Security Specialty).
• Knowledge of AI model explainability and ethical AI standards.

AI71 is an equal opportunity employer. We embrace diversity and are committed to creating an inclusive environment for all employees.