Engineer - Agents & Evals

TL;DR - We’re looking for strong engineers (backend, frontend, or full-stack) who are excited about building agents. You’ll help shape how we build, evaluate, orchestrate, and scale LLM-powered agents in production - and define what it means to create truly lovable AI products. Why Lovable? Lovable lets anyone and everyone build software with plain English. From solopreneurs to Fortune 100 teams, millions of people use Lovable to transform raw ideas into real products - fast. We are at the forefront of a foundational shift in software creation, which means you have an unprecedented opportunity to change the way the digital world works. Over 2 million people in 200+ countries already use Lovable to launch businesses, automate work, and bring their ideas to life. And we’re just getting started. We’re a small, talent-dense team building a generation-defining company from Stockholm. We value extreme ownership, high velocity and low-ego collaboration. We seek out people who care deeply, ship fast, and are eager to make a dent in the world. What we’re looking for Core requirement: Strong engineering fundamentals. You might be backend, frontend, or full-stack - what matters most is your ability to build high-quality production systems. Big plus if you: Have built AI agents yourself (side projects count) Are deeply curious about how AI systems behave and improve Have worked with LLMs or AI systems in production Are excited about experimenting with new models and techniques Experience that stands out: Shipped ML or AI features to real users with uptime requirements Built evaluation systems or ML experimentation pipelines Strong opinions on safety, latency, and helpfulness - but open to testing and learning What you’ll do In one sentence: Build, tune, and scale agents that power lovable products. Add new agent skills and tools Improve agent reasoning, orchestration, and efficiency Design how multiple agents collaborate Select the right models for different task types Push the limits of what agents can reliably do in real products Analyze agent behavior and performance “Hill-climb” toward better helpfulness, safety, and reliability Build evaluation frameworks and benchmarks Create experimentation pipelines and feedback loops Ensure agents perform well across real-world use cases Our tech stack We're building with tools that both humans and AI love: React, Golang, and Rust Serverless primitives on Cloudflare, k8s, GCP, Modal, Temporal How we hire Fill in a short form then jump on an initial exploratory call. Join us for a round of technical interviews Team intro calls with the team About your application Please submit your application in English - it’s our company language so you’ll be speaking lots of it if you join We treat all candidates equally - if you’re interested please apply through our careers portal Ready to join us? Help us unlock human creativity and build the future of software creation. Apply for this position