Key Skills

Job Description

Write, host, and run the services behind our models, from model downloads and CI to our own servers and the ones customers run our models on. About Desert Ant Labs Desert Ant Labs is an on-device AI lab in Europe. We're building efficient frontier intelligence, bottom up. We make the fastest model for each task, built to run on the billions of phones, laptops, and browsers people already own. Every model is lightning fast and private, and has no per-call cost. Little brains in every product. With our native SDKs for Swift, Kotlin, and JavaScript, you add a model to an app in a few lines of code. Data stays with your customer, and the feature works without a cloud provider. Every role here pushes the limits of what a phone or a laptop can do. About the role Our models run on the device. Getting them to developers takes a cloud: developers download model files from our storage and from Hugging Face, the SDKs send one usage count a day, every SDK release builds and tests on Apple platforms, Android, Windows, Linux, and the web, and some customers run our models on their own servers. You write the services behind all of it, host them, and keep them running, with the engineering team. We run on Scaleway and on our own servers in racks we manage, with CI on GitHub Actions. We keep the setup portable between providers, so it also runs on the clouds our customers use. The goal is fast model downloads everywhere, releases that build and test in minutes, and our models running on a server as easily as on a phone. What you will do Write and run the services that store and deliver model files, so every download is fast and verified. Write and run the service that receives the SDKs' daily usage counts, and keep it private and cheap to run. Write the internal tools and small services the team asks for, and maintain them after they ship: updates, fixes, and tests. Build and keep up CI for every SDK and model release: macOS, Windows, Linux, Android, and the web. Package and deploy our models for servers: containers, serverless functions, and the inference hosts customers pick. Set up our own servers from scratch: operating system installs, users and permissions, networking, and updates. Keep our websites and internal tools running: deploys, DNS, access, secrets, and monitoring. Work with the research team on the path from a trained model to a published release. You might be a fit if you Have written backend services and kept them running in production: the code, the deploys, and the fixes when they broke. Know at least one cloud deeply, like Scaleway, AWS, Google Cloud, or another provider, and keep what you build on it portable to another one. Have set up Linux servers from scratch, physical or managed: installs, users and permissions, SSH, firewalls, and updates. Have built CI and release pipelines that other engineers trust, including macOS and Windows builds. Manage infrastructure as code, and automate a task the second time you do it by hand. Know what a service logs and what a month of it costs. Write clean, tested code, and spot a weak change in review, whether a person or an agent wrote it. Plan and run your work through coding agents such as Claude Code, with a low tolerance for slop, and keep trying new ways to work with them that make the team faster without lowering the bar. Bonus points Racked, cabled, or replaced parts in physical servers. Served ML models on CPU or GPU servers, or in serverless functions. Ran build machines for mobile or desktop apps. How we work We're a small, flat team, and we build the models, the SDKs, and the apps that use them. Detail and Subwave, our own apps, run our models in production. Start what needs starting without waiting to be asked, and finish what you start. Take on work outside your role when a project needs you. We ship quickly, so we cut scope until only the part users notice is left. Anyone can comment on your work or redo your draft, and we say early when work isn't ready. We read that feedback as help. We judge the work by what shipped and what changed because of it. Nobody counts hours. What we offer Salary and equity, based on level. In our Amsterdam office, or remote anywhere between Eastern Time in North America (UTC-5) and Central European Time (UTC+1), so everyone shares part of the working day. Recruiters and agencies We hire directly. We don't reply to emails from recruiters or agencies, and we don't want their outreach about this role or any other. Location: Amsterdam or Remote (UTC-5 to UTC+1) Apply on our site: https://desertant.com/jobs/backend-and-infrastructure-engineer/

Core Responsibilities

Build, deploy, and maintain backend services for model storage and delivery, usage reporting, internal tools, and customer-facing inference deployments. Manage portable cloud and physical-server infrastructure, CI and release pipelines across platforms, and the operational needs of websites and internal tools.

Requirements

Candidates should have production experience building and operating backend services, deep knowledge of at least one cloud provider, and hands-on experience setting up Linux servers and maintaining infrastructure as code. They should also have built trusted CI and release pipelines, write and review clean tested code, and use coding agents effectively while maintaining high quality.

Benefits

• Salary
• Equity