AI Safety Specialist (AI Engineering)

The AI Safety Specialist (AI Engineering) at Hyphen Connect is a pivotal role focused on enhancing the security and robustness of language models. This position involves working within a dynamic team dedicated to ensuring the safe deployment of AI systems, aligning with the company's commitment to ethical AI practices.

Key responsibilities include conducting adversarial testing on large language models (LLMs) and multimodal agents to identify vulnerabilities. The specialist will implement guardrails and real-time filtering mechanisms for autonomous tool usage, ensuring AI behaviors adhere to established ethical guidelines. Additionally, the role involves developing constitutional AI principles and assisting with reinforcement learning from human feedback (RLHF) alignment pipelines.

Candidates should possess 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 in AI behavior.

Hyphen Connect offers a collaborative work environment that values innovation and ethical AI development. Employees have opportunities for professional growth and are encouraged to contribute to the company's mission of delivering secure and responsible AI solutions.