ElevenLabs · 4 days ago

AI Safety Engineer

United States

Full-time

Remote

Senior Level

6+ years exp

Maximize your interview chances

Artificial Intelligence (AI)Content Creators

Insider Connection @ElevenLabs

Discover valuable connections within the company who might provide insights and potential referrals.
Get 3x more responses when you reach out via email instead of LinkedIn.

Responsibilities

Architect, build, and maintain our anti-abuse and content moderation infrastructure designed to protect us and end users from unwanted behavior.

Lead the adoption of latest gen AI methods to automate our abuse monitoring and content moderation workflows;

Design, implement and iterate ML models using proprietary and industry tools to continuously improve our detection and enforcement capabilities

Collaborate with broader engineering team to design and build safety mitigations across our product suite; develop ubiquitous moderation coverage across our deployments

Expand our internal safety tooling and infrastructure

Implement provenance solutions in partnership with internal and external partners.

Collaborate with our data team to develop and maintain actionable safety metrics

Qualification

Find out how your skills align with this job's requirements. If anything seems off, you can easily click on the tags to select or unselect skills to reflect your actual expertise.

Machine LearningPythonAI SafetyPytorchSQLData AnalysisGenerative AIAI Provenance ToolsReactBackend ServicesData PipelinesMentoringTechnical Communication

Required

6+ years in progressively senior software engineering roles, including at least some spent in trust and safety, integrity or AI safety teams

Strong experience in Python, including asynchronous Python. Proven track record of building production Python applications.

Experience/proven track record with: Building backend safety infrastructure & tooling; designing, implementing, and iterating on ML/AI models to detect, monitor and enforce on abusive content; machine learning frameworks such as Pytorch

Experience and/or interest in applying generative AI to increase moderation efficiency

Experience and/or interest in designing and implementing AI provenance tools

Experience with SQL and data analysis tools; familiarity with React would be useful

Preferred

Setting up and maintaining production backend services and data pipelines.

Designing and implementing trust and safety operational flows (ie flagging, actioning, recording)

Experience mentoring and leading technical teams

Benefits

Competitive compensation package including stock options; we want you to have ownership in the company and share the successes that lie ahead. That’s why we offer early employees stock options as part of their compensation package.

Remote-first; we look at who you are rather than where you live. We currently have offices in NYC, London, and Warsaw.

Huge impact; you will be responsible for designing industry-leading solutions in AI safety in one of the world’s most exciting AI startups.

Extraordinary team; we favor ambitious, smart people striving for outsized impact. You’ll work on the state of the art surrounded by people with extraordinary skills and positive attitudes.

Annual company off-sites; previous locations included Croatia, Portugal and Switzerland.