On-Device AI Engineer for Android Automotive

Applied Intuition Inc.; Sunnyvale (CA); On-site; USD 150,000 - 250,000; Full time

Benefits offered by this job

Equity

Health benefits

401k retirement

Job summary

Applied Intuition is seeking an embedded ML engineer to own the end-to-end lifecycle of on-device ML systems for Android Automotive. You will deploy production ML inference, optimize for tight latency and memory budgets, and integrate models using TensorFlow Lite/ONNX Runtime while interfacing with vehicle signals via C++.

The role requires strong C++, JNI, and experience with edge constraints, aiming to ensure safe and predictable model behavior in production vehicles.

Qualifications

• BS, MS, or PhD in Computer Science, Electrical Engineering, or related technical field.
• 3+ years shipping ML inference on embedded/mobile/auto platforms.
• Strong proficiency in C++ and native Android integration (JNI).
• Expertise in model optimization: quantization, pruning, compilation.
• Experience integrating LLM function calling with structured outputs.
• Hands‑on experience with Android system services or Android Automotive OS.

Responsibilities

• Deploy and run production-grade ML inference on Android Automotive (AAOS).
• Implement on-device multimodal LLMs and safe dispatch to local vehicle APIs.
• Integrate models with TensorFlow Lite, ONNX Runtime, or vendor SDKs.
• Profile and optimize models for latency, memory, power, and thermal budgets.
• Interface with vehicle signals, sensors, and system services using C++.

Skills

C++

JNI

Embedded ML

On-device AI

Model optimization

LMM integration

Android AAOS

Education

BS/MS/PhD in CS or EE

Tools

TensorFlow Lite

ONNX Runtime

Job description

Applied Intuition is seeking an embedded ML engineer to own the end-to-end lifecycle of on-device ML systems for Android Automotive. You will deploy production ML inference, optimize for tight latency and memory budgets, and integrate models using TensorFlow Lite/ONNX Runtime while interfacing with vehicle signals via C++.

The role requires strong C++, JNI, and experience with edge constraints, aiming to ensure safe and predictable model behavior in production vehicles.