Job responsibilities:
- Conduct AI red teaming exercises and security inference testing against AI/ML Models and LLMs to simulate adversarial attacks and ensure system resilience.
- Execute creative security solutions, design, development, and technical troubleshooting to build solutions and break down technical problems.
- Develop secure and high-quality production code, review, and debug code written by others.
- Minimize security vulnerabilities by evolving security protocols and creating processes to assess current controls.
- Work with stakeholders to understand security needs and recommend business modifications during periods of vulnerability.
- Add to team culture of diversity, equity, inclusion, and respect.
Required qualifications, capabilities, and skills:
- Formal training or certification on security engineering concepts and 5+ years applied experience
- Extensive Python coding and development experience.
- Expertise in securing AI/ML systems with understanding in AI technologies like Python, TensorFlow, and PyTorch.
- Experience conducting AI red teaming exercises against LLMs to test system resilience.
- Understanding of infrastructure as code (IaC) tools like Terraform.
- Solid understanding and practical experience across the model development lifecycle (MDLC).
- Solid understanding of cloud computing concepts with AWS or other cloud platforms and container orchestration tools.
Preferred qualifications, capabilities, and skills:
- Experience with Java, Spring, and Spring Boot frameworks.
- Skilled in MySQL and SQL, capable of writing and maintaining stored procedures.
- Knowledgeable in microservices architecture and API security.
- Familiar with AI safety, alignment, cybersecurity concepts, and GenAI security.