GenAI Safety Tech Lead

Alice • New York, NY

5d

About The Position

Alice is seeking a driven, detail-focused professional to take on a leading role in our team as a GenAI Safety Tech Lead. In this role, you'll dive into the cutting-edge of technology, meticulously analyzing various content infringements to secure the new wave of Generative AI tools, while owning the end-to-end delivery of engagements from planning through execution and quality assurance. Your duties will include collaborating with experts in diverse fields such as Hate Speech, Misinformation, Intellectual Property and Copyright, among others. Your tasks will involve writing adversarial prompts to identify weaknesses in various AI models, including Large Language Models (LLMs), Text-to-Image, Text-to-Video, AI Agents and beyond. You'll also oversee data management to guarantee the highest quality of outputs, bringing a proven track record of managing complex projects from the ground up.

Requirements

• 5+ years of experience in AI Safety and/or Responsible AI and/or Trust and Safety.
• Proven track record of managing projects end-to-end, from planning and execution through quality assurance to final delivery.
• Experience leading projects with multiple stakeholders in fast-paced, variable environments.
• Experience working directly with clients, including attending client meetings and helping manage those relationships day to day.
• Familiarity with recent Generative AI models and agents is essential, though direct technical experience is not a prerequisite.
• Strong attention to detail, organizational capabilities, and the capacity to juggle numerous tasks concurrently.

Nice To Haves

• Proven track record of research in academia or at a research institute.
• Experience with various model types (Text-to-Text, Text-to-Image) is desirable.
• Prior experience with OSINT (Open Source Intelligence) will be considered an asset.
• Experience mentoring or leading junior team members.
• A self-starter attitude, with the energy to excel in a fast-moving and variable environment.

Responsibilities

• Developing adversarial and risky prompt strategies across several areas of abuse to expose potential vulnerabilities in models.
• Owning projects end-to-end - from initial planning and execution through quality assurance to final delivery - with accountability for outcomes.
• Mentoring junior analysts and promoting a culture of knowledge exchange and continual learning within the team.
• Managing extensive datasets across multiple languages and areas of abuse, ensuring precision and meticulous attention to detail.
• Ongoing investigation into new tactics for circumventing foundational models' safety measures.
• Partnering with cross-functional teams - engineering, product, policy - to tackle new challenges and craft forward-thinking strategies and resolutions.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed