Embedded AI Engineer – Android Automotive (On-Device Intelligence)
Applied Intuition is seeking an Embedded AI Engineer to develop on-device intelligence for a next-generation Android Automotive platform. This role involves managing the entire lifecycle of embedded machine learning systems, ensuring they operate predictably and safely under real-world constraints such as latency, thermal limits, and functional safety.
Key responsibilities include deploying and running production-grade ML inference and learning systems on Android Automotive OS (AAOS), implementing on-device multimodal large language models (LLMs), and integrating models using TensorFlow Lite, ONNX Runtime, or specialized vendor SDKs. The engineer will also profile and optimize models to meet strict latency, memory, power, and thermal budgets, instrument runtime performance across CPU, GPU, and NPU acceleration layers, design safety boundaries for model outputs, and interface directly with vehicle signals, sensors, and system services using C++ and JNI.
The ideal candidate will have a BS, MS, or PhD in Computer Science, Electrical Engineering, or a related technical field, along with over three years of experience shipping ML inference on embedded, mobile, or automotive platforms. Strong proficiency in C++ and experience with native Android integration (JNI) are essential. Expertise in model optimization techniques such as quantization, pruning, and compilation, as well as experience integrating LLM function calling or tool execution with structured outputs, is required. Hands-on experience with Android system services or AAOS and a deep understanding of edge constraints, including real-time behavior and memory pressure, are also necessary.
Preferred qualifications include experience with Snapdragon Automotive, ARM Ethos, or specialized NPU pipelines; a background in running quantized LLMs on-device using llama.cpp or TFLite transformers; familiarity with functional safety concepts (ISO 26262), sandboxing, or policy enforcement; and experience bridging cloud-trained models to resource-constrained embedded runtimes.
Compensation for this full-time position includes a base salary ranging from $150,000 to $250,000 annually, equity in the form of options and/or restricted stock units, comprehensive health, dental, vision, life, and disability insurance coverage, 401(k) retirement benefits with employer match, learning and wellness stipends, and paid time off.