LLM Safety & Alignment Engineer

Hyphen Connect Limited; San Francisco (CA); On-site; USD 100,000 - 130,000; Full time

Job summary

Hyphen Connect Limited is seeking an AI Safety Specialist in San Francisco, California, to enhance the security and robustness of language models. This role involves conducting adversarial testing, implementing protective measures, and ensuring AI behavior aligns with ethical principles.

The ideal candidate will have a background in cybersecurity or adversarial ML and experience with automated red-teaming frameworks. Strong analytical skills are essential for identifying edge cases and supporting safe deployment of AI systems.

Qualifications

• Knowledge in prompt engineering or adversarial ML is essential.
• Experience in automated red-teaming frameworks is preferable.
• Ability to identify edge cases through strong analytical skills.

Responsibilities

• Conduct adversarial testing on LLMs and multimodal agents.
• Implement guardrails and real-time filtering for autonomous tool use.
• Develop constitutional AI principles and assist with RLHF alignment pipelines.

Skills

Background in cybersecurity

Experience with jailbreak taxonomies

Strong analytical mindset

Job description

Hyphen Connect Limited is seeking an AI Safety Specialist in San Francisco, California, to enhance the security and robustness of language models. This role involves conducting adversarial testing, implementing protective measures, and ensuring AI behavior aligns with ethical principles.

The ideal candidate will have a background in cybersecurity or adversarial ML and experience with automated red-teaming frameworks. Strong analytical skills are essential for identifying edge cases and supporting safe deployment of AI systems.