What are the responsibilities and job description for the Specialist, Offensive AI Security - Red Team position at Samsung Research America?
Lab Summary:
Samsung Knox™ (https://www.samsungknox.com/) is Samsung’s guarantee of security, and a secure device gives you the freedom to work and play how, where, and when you want. Samsung Knox consists of a highly secure platform built into a variety of Samsung devices, including Samsung’s mobile phones and laptop computers.
Come join the Samsung KNOX team and help us define and develop the future core technologies for Samsung devices and services!
Position Summary:
We are looking for an Offensive AI Security Specialist to tackle the evolving security challenges in AI and machine learning systems. You will define security methodologies, identify threats to AI models, and develop tools to ensure the robustness of our AI features
Position Responsibilities:
- Define and implement AI security methodologies for safeguarding AI models
- Analyze Samsung mobile AI features and identify potential vulnerabilities
- Develop automated tools using AI for vulnerability discovery, such as AI-driven fuzzing solutions
- Research security threats and attack vectors targeting machine learning models
- Simulate adversarial attacks, including data poisoning and input manipulation, to strengthen AI resilience
- Collaborate with teams to improve AI features and ensure adherence to AI security best practices
Required Skills:
- Bachelor’s degree in Computer Science, Cybersecurity, or a related field, or equivalent combination of education, training, and experience
- 5 years of experience in AI/ML security or vulnerability research
- Proficiency in Python, TensorFlow, or PyTorch, with experience in adversarial machine learning
- Familiarity with Red Team rules of engagement & best practices
- Strong communication, documentation, and reporting skills
Special Attributes:
- Experience with AI fuzzing tools and securing AI pipelines
- Familiarity with AI ethics/safety policies and privacy-preserving AI methodologies
- Proficiency with RAG, Quantization, Fine-Tuning, and other practical LLM development skills
