Mobile Engineer: Android

Desert Ant Labs; Netherlands; Hybrid; EUR 90,000 - 120,000; Full time

Benefits offered by this job

Equity

Remote work options

Amsterdam office

Job summary

Desert Ant Labs is seeking a skilled Android/Kotlin engineer to build and optimize our Kotlin SDK for running models on Android devices. You will ensure consistency with Apple platforms, profile across LiteRT and ONNX Runtime, and test extensively across device labs. Strong Kotlin, NDK/JNI, and performance tuning are essential.

Amsterdam office or remote options available. The role emphasizes shipping high-quality, fast inference on diverse chips and drivers, with a focus on real-world latency

Qualifications

• Fluent Kotlin development experience.
• Proficient with NDK/JNI and Android libraries.
• Strong profiling and performance optimization skills.

Responsibilities

• Build the Kotlin SDK and release to Maven Central.
• Ensure consistency of model results across Android and Apple platforms.
• Profile and speed up inference across Android runtimes and hardware accelerators.
• Test on devices ranging from budget to flagship using device labs and Firebase Test Lab.

Skills

Kotlin

Jetpack Compose

NDK

JNI

Profiling

Android library

Education

Bachelor's degree in Computer Science or equivalent

Tools

TensorFlow Lite

LiteRT

ONNX Runtime

NNAPI

JNI

Job description

Build our Kotlin SDK, and find the fastest way to run each model on each Android chip.

About Desert Ant Labs

About the role

You work on our Kotlin SDK, which runs our models on Android, on LiteRT today. The first goal is every model on Android by December.

Android phones use hundreds of different chips, NPUs, and drivers. You speed up each model, across audio, vision, and text, until the model meets its latency target on a budget phone as well as on a flagship. Deep Android performance experience matters more here than machine learning experience.

What you will do

• Build the Kotlin SDK: API design, releases to Maven Central, tests, and docs.
• Keep every model's results on Android the same as on Apple platforms.
• Profile and speed up inference on Android runtimes such as LiteRT and ONNX Runtime: delegates, NPUs, GPUs, and memory.
• Test on everything from budget phones to flagships, in Firebase Test Lab and in our own device lab.

You might be a fit if you

• Have shipped Android apps or libraries with a large user base, and made them measurably faster: startup, rendering, memory, or battery.
• Write fluent Kotlin, know Jetpack Compose, and use the NDK when a runtime needs native code.
• Profile before you optimize.
• 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.
• Know which NPUs exist, where LiteRT delegates speed up a model, and where the delegates fail.
• Integrated an on-device model with TensorFlow Lite, LiteRT, ONNX Runtime, ExecuTorch, MediaPipe, or NNAPI.
• Wrote JNI or native code.
• Maintained an Android library that outside developers used.

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.

Location: Amsterdam or Remote (UTC-5 to UTC+1)