Trust & Safety Engineer

Lovable; Town of Stockholm (NY); On-site; USD 180,000 - 250,000; Full time

Job summary

Lovable seeks a senior engineer to build and operate a fraud platform that protects payments, credits, and free access from abuse. You will design real-time signals and scoring, deploying decisions within milliseconds and rapidly iterating with feedback from trust & safety.

You will model attackers, balance precision/recall, and defend users without hindering legitimate activity. Join a fast-moving team driving secure, scalable software.

Qualifications

• 5+ years building anti-fraud, anti-abuse, or risk systems at consumer scale.
• Strong backend engineering in Go, Python, or TypeScript, with data-driven mindset.
• Experience disrupting sophisticated fraud campaigns and using rules engines, feature stores, and ML scoring.
• You think in adversaries, model attackers, and measure impact before they adapt.
• Pragmatic about precision/recall trade-offs to protect users without harming them.

Responsibilities

• Design and ship the fraud platform that protects Lovable's payments, credits, and free tier from abuse.
• Build real-time detection: signals, features, scoring, and decisioning with millisecond latency.
• Run a tight feedback loop with chargebacks, support, and trust & safety to label, learn, and redeploy weekly.
• Stand up bot defenses across signup, app generation, and publishing without breaking legitimate users.
• Own the metrics that matter: fraud loss rate, false-positive rate, attacker time-to-defeat.

Skills

Anti-fraud systems

Backend engineering

Go/Python/TypeScript

Real-time data processing

ML scoring and signals

Tools

Rules engines

Feature stores

ML platforms

Job description

TL;DR Millions of people build on Lovable every month. A small fraction try to abuse it. You'll build the adaptive systems that stop monetary fraud, platform abuse, and bot attacks before they reach our users.

Why Lovable?

Lovable is the software creation platform that gives people the power to act on the problems closest to them. For decades, turning an idea into software required so much capital, technical fluency, and time that many ideas never came to life. Lovable is the counterargument: a platform for all people with ideas, ambition, and problems worth solving. From solopreneurs to small business owners to teams at companies like Adidas and Zendesk, people have built over 60 million projects on Lovable since its launch in November 2024. And we’re just getting started.

We’re building a generational company from Stockholm, with growing teams in London, Boston, New York, and San Francisco. Our team is small, talent-dense, and moving quickly, with a culture rooted in extreme ownership, high velocity, and low-ego collaboration. We look for people who care deeply, ship fast, and are eager to make a dent in the world.

Lovable is one of TIME’s 100 Most Influential Companies and has been recognized on the Forbes AI 50 and CNBC Disruptor 50, reflecting our momentum as one of Europe’s fastest-growing AI companies and one of the most ambitious places to build in this next era of software.

What we're looking for

• 5+ years building anti-fraud, anti-abuse, or risk systems at consumer scale (payments, marketplaces, fintech, or large social platforms).

• Strong backend engineering - Go, Python, or TypeScript - and comfort working close to the data.

• Experience with disrupting sophisticated fraud campaigns and attacks, knowledge of rules engines, real-time feature stores, ML scoring, device fingerprinting, and behavioral signals.

• You think in adversaries: you can model an attacker, ship a counter, and measure it before they adapt.

• Pragmatic about precision/recall trade-offs. You protect users without punishing them.

• Bonus: experience with LLM-specific abuse (prompt injection at scale, generated-content fraud, credit farming) or with chargeback and payments fraud at a Stripe/Adyen/Braintree-scale merchant.

What you'll do

• Design and ship the fraud platform that protects Lovable's payments, credits, and free tier from abuse.

• Build real-time detection: signals, features, scoring, and decisioning that act in milliseconds.

• Run a tight feedback loop with chargebacks, support, and trust & safety to label, learn, and re-deploy weekly.

• Stand up bot defenses across signup, app generation, and publishing - without breaking legitimate users.

• Own the metrics that matter: fraud loss rate, false-positive rate, attacker time-to-defeat.