Description

You will design and secure large language model systems, focusing on safety, bias mitigation, and vulnerability assessment.

Responsibilities

• Identify and remediate vulnerabilities within LLM architectures and deployment pipelines.
• Conduct red teaming exercises to evaluate model resilience against adversarial attacks.
• Implement anomaly detection mechanisms to monitor system integrity and data quality.
• Assess and mitigate bias, discrimination, and other safety issues in AI outputs.

Required Skills

• 10+ years of experience in Machine Learning engineering.
• Deep expertise with Large Language Models (LLMs) and generative AI.
• Proven track record in AI security, red teaming, and vulnerability identification.
• Strong understanding of AI ethics, bias detection, and safety frameworks.
• Proficiency in anomaly detection techniques and tools.
• Any Graduate degree in Computer Science, Engineering, or related field.

Preferred Skills

• Experience with automated red teaming tools and frameworks.
• Background in deploying LLMs at scale in production environments.

Key Skills

Education

Any Graduate