AI Product Engineer

SafetyKit replaces human Trust & Safety reviewers with language models. Companies like Character.ai, Substack, Upwork, Faire, and Eventbrite use SafetyKit to find and remove bad content.

We use language models to solve real business problems and our users pay us real money. It turns out that's a lot of fun!

Here's what we're looking for:

Responsibilities: • Doing the plumbing that makes the magic happen. We need web scrapers, document ingestors, LLM eval tools, and more, and they all need to be fast and reliable • Working with our users to translate their complex, nuanced policies into SafetyKit models. • Quickly experimenting with and deploying new AI technologies. New open-source vision model lands that outperforms the state-of-the-art? We're testing, integrating, and shipping it today

Your skills: • You're fast and confident in Typescript (or able to get there quickly) • You love Postgres and SQL (or are able to do so quickly) • You like AWS services like Lambda and Step Functions • You're a creative and careful thinker. • You're excited to work together in our San Francisco office five days a week.

Bonus Points: • Prior experience as an early/founding engineer at a start-up • Experience with language models and vision models

We want you to join our team! There's so much our users need us to do, so much cool AI product to build, and so many prompts to engineer.

About SafetyKit: We're ex-Stripe and Airbnb, repeat founders, and have deep connections and experience in our space. We work in-person in a beautiful office in the Mission in San Francisco.

Full automation is here, but it's our job to evenly distribute it. We're hiring the fastest product engineers in the world to ship tools like web crawlers, video pipelines, and no-code workflow builders so our users can integrate instantly. We have paying users like Substack and Lime, and a long list of companies that need our help.