Android Application Engineer

LILT•Indianapolis, IN

13h

About The Position

LILT AI is changing how the world communicates — and LILT is leading that transformation. We're on a mission to make the world's information accessible to everyone , regardless of the language they speak. We use cutting-edge AI, machine translation, and human-in-the-loop expertise to translate content faster, more accurately, and more cost-effectively without compromising on brand, voice, or quality. At LILT, we empower our teammates with leading tools, global collaboration, and growth opportunities to do their best work. Our company virtues— Work together, win together; Find a way or make one; Quicker than they expect; Quality is Job 1 —guide everything we do. We are trusted by Intel Corporation , Canva , the United States Department of Defense , the United States Air Force , ASICS , and hundreds of global Enterprises. Backed by Sequoia, Intel Capital, and Redpoint, we’re building a category-defining company in a $50B+ global translation market being redefined by AI. LILT is looking for an Android Application Engineer to join the team building LILT Converse, our on-device instant translation application. Converse enables secure, real-time speech translation without an internet connection — making it the go-to solution for government, defense, and enterprise teams operating in communication-sensitive or connectivity-constrained environments. You will work at the intersection of cutting-edge on-device AI and polished mobile UX, building software that runs large multilingual speech models directly on Android hardware leveraging Qualcomm Snapdragon AI acceleration. This is a high-impact role on a product that is moving quickly. As the Android engineer on Converse, you will own the Android application end-to-end — from architecture and on-device ML integration through performance tuning, release, and reliability in the field — working closely with ML, product, and design on a small senior team. You will architect new features, integrate on-device ML models, optimize performance, manage large local model assets, and ensure rock-solid reliability in the field. You will ship capabilities like multilateral translation (simultaneous 3+ language conversations), utterance management, kiosk deployment modes, and enterprise configuration. You will be comfortable reasoning about hardware constraints, APK packaging, sideloading workflows, and the tradeoffs of running multi-gigabyte inference workloads on mobile SoCs. We are looking for someone who thrives in a fast-moving startup environment and takes pride in shipping software that works in the real world under demanding conditions.

Requirements

4+ years of professional Android development (Kotlin), with a track record of owning a production Android app end-to-end — architecture, implementation, release, and field reliability
Strong Android fundamentals: Android SDK, Jetpack, lifecycle, background work, and storage APIs
Experience integrating native libraries via NDK/JNI (ML runtimes, audio engines, or similar)
Comfort optimizing performance on physical devices — memory, latency, thermal behavior under sustained workloads
Experience with offline-first applications and large on-device assets (multi-GB model files, packaging, sideloading)
Real-time audio on Android: microphone capture, TTS/speaker output, and low-latency audio pipelines (including USB microphone support)
On-device speech pipeline integration: wiring ASR → translation → TTS, handling streaming partial results, and managing turn-taking in a live conversation UI
Enterprise deployment familiarity: sideloading, MDM/kiosk modes, pre-provisioned device configuration
Bias toward shipping reliable software in demanding, real-world conditions

Nice To Haves

On-device ML runtime integration (ONNX Runtime, TensorFlow Lite, or Qualcomm QNN / Snapdragon NPU acceleration)
External display / kiosk UX (HDMI output, presentation layers, broadcast-style overlays)
Secure data handling: encrypted export, USB storage workflows, air-gapped or connectivity-constrained environments
Prior work with government, defense, or enterprise customers
Deep speech/audio domain expertise beyond app integration — e.g. tuning latency/quality tradeoffs, noise handling and audio preprocessing, model quantization on mobile SoCs, or direct work with speech model runtimes
iOS / Swift experience
CI/CD with hardware-in-the-loop testing on physical devices

Responsibilities

Architect new features
Integrate on-device ML models
Optimize performance
Manage large local model assets
Ensure rock-solid reliability in the field
Ship capabilities like multilateral translation (simultaneous 3+ language conversations), utterance management, kiosk deployment modes, and enterprise configuration
Reason about hardware constraints, APK packaging, sideloading workflows, and the tradeoffs of running multi-gigabyte inference workloads on mobile SoCs