AI Safety Specialist (AI Engineering)

The AI Safety Specialist (AI Engineering) role at Hyphen Connect focuses on enhancing the security and robustness of language models within the company's AI systems. This position is integral to ensuring the safe deployment of AI technologies by conducting adversarial testing, implementing protective measures, and aligning AI behavior with ethical principles.

Key responsibilities include conducting adversarial testing on large language models (LLMs) and multimodal agents to identify vulnerabilities. The specialist will also implement guardrails and real-time filtering mechanisms for autonomous tool use, ensuring that AI systems operate within defined safety parameters. Additionally, the role involves developing constitutional AI principles and assisting with reinforcement learning from human feedback (RLHF) alignment pipelines to maintain ethical AI behavior.

Candidates should have a background in cybersecurity, prompt engineering, or adversarial machine learning. Experience with jailbreak taxonomies and automated red-teaming frameworks is essential. A strong analytical mindset is required to effectively identify and address edge cases that may arise in AI system deployment.

Hyphen Connect offers a dynamic work environment where innovation and safety in AI development are prioritized. Employees have opportunities for professional growth and are encouraged to contribute to the advancement of secure and ethical AI technologies.