At SafetyKit, we use language models to tackle real-world risk and compliance challenges for some of the world's leading companies. Our technology helps teams build, refine, and enforce complex policies (think regulated goods, brand guidelines, and everything in between).
We work for payment processors and marketplaces including Upwork, Faire, Patreon, Character.ai, Substack, and Eventbrite. We built a product our users love—now they want more. We’re growing fast to meet demand and we need talented engineers to help shape the next generation of AI-powered trust and safety.
You are thoughtful, opinionated, and fast. You can own the product pipeline, from user interviews to design to pushing code that the engineering, policy, and operation teams using SafetyKit will love.
Responsibilities
-
Build fast and reliable infrastructure (LLM evaluation, web crawling, document ingestion, etc.) that protects organizations and their end users
-
Getting to know our users and their policies deeply: understanding what they care about, then building language model decision flows that capture those complexities
-
Quickly experimenting with and deploying new AI technologies. Newly deployed vision model lands that outperforms the state-of-the-art? We need to test, integrate, and ship it today
Your skills
-
You’re fast and confident in Typescript (or able to get there quickly)
-
You love Postgres and SQL
-
You like serverless AWS services like Lambda and Step Functions
-
You love talking to users and learning about their weird and complex business problems
-
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
About the interview
We keep our interview process minimal:
-
45min intro call and remote coding interview (Talk about your background, learn about SafetyKit, do some Leetcode).
-
On-site in our office in San Francisco. Meet the team, do some architecture white boarding and draw some boxes, do some more coding and some APIs, and have a really good lunch.
-
We make decision/offer the day of your onsite.
Similar Jobs
.png)
What We Do
We build AI agents for Risk and Compliance that do complex workflows like underwriting and investigations. Trusted by the world's largest marketplaces and payments companies.
