Description

You will design and implement security measures to protect AI models from adversarial attacks, prompt injection, and jailbreaking attempts.

Responsibilities

• Design and implement security controls to defend AI models against adversarial attacks, prompt injection, and jailbreaking.
• Develop data protection mechanisms and data loss prevention capabilities to prevent exposure of sensitive information.
• Create and maintain API services for AI security tools using modern frameworks.
• Build monitoring solutions for AI security posture assessment and integrate security controls into ML/AI workflows.
• Document security processes, architecture, and implementation details.

Required Skills

• 8+ years of experience building enterprise-grade full-stack applications.
• Strong hands-on development experience in Java or Python.
• Experience with unit testing frameworks such as JUnit or Pytest.
• 5+ years of experience in API development using REST or gRPC methodologies with FastAPI, Spring REST, or similar frameworks.
• 5+ years of experience developing and maintaining cloud-native applications using Kubernetes or other container management solutions.
• Experience with the development, deployment, performance tuning, and maintenance of AI models and applications on cloud platforms.
• Proficiency with AWS Bedrock, AWS SageMaker, and both open-source and custom AI/ML models.
• Experience with Terraform and Helm charts.
• Knowledge of Data Science and AI/ML training and inference platforms.
• Experience with React or Angular frameworks.

Key Skills

Education

Any Gradute