Embedded AI Engineer Android Automotive On Device Intelligence
Posted Updated 6
views
Summary
Deploy production ML inference and multimodal LLMs on Android Automotive using C++ and JNI. The role involves optimizing model performance across hardware layers (CPU, GPU, NPU) and integrating AI with vehicle signals and system services.
You will deploy production ML inference and learning systems on Android Automotive. You will implement multimodal LLMs, integrate model runtimes, optimize performance within hardware limits, instrument acceleration layers, design output guardrails, and connect models to vehicle signals and services using C++ and JNI.
Responsibilities
- Deploy ML inference and learning systems on Android Automotive
- Implement on-device multimodal LLMs and safe local vehicle API dispatch
- Integrate models using TensorFlow Lite, ONNX Runtime, or vendor SDKs
- Optimize models for latency, memory, power, and thermal limits
- Instrument runtime performance across CPU, GPU, and NPU layers
- Design guardrails, allowlists, and fallback logic for model outputs
- Interface with vehicle signals, sensors, and system services using C++ and JNI
Requirements
- BS, MS, or PhD in Computer Science, Electrical Engineering, or a related technical field
- 3+ years of shipping ML inference on embedded, mobile, or automotive platforms
- C++ proficiency and native Android integration experience using JNI
- Expertise in quantization, pruning, and compilation
- Experience with LLM function calling or tool execution using structured outputs
- Experience with Android system services or Android Automotive OS
- Understanding of real-time behavior and memory pressure on edge devices
Benefits
- Equity
- Health insurance
- Dental insurance
- Vision insurance
- Life insurance
- Disability insurance
- 401k employer match
- Learning stipend
- Wellness stipend
- Paid time off