Embedded AI Engineer – Android Automotive (On-Device Intelligence)

About the role

Applied Intuition is building on‑device intelligence for the next‑generation Android Automotive platform. As an Embedded AI Engineer you will own the full lifecycle of embedded machine‑learning systems, ensuring they run safely and predictably under real‑world constraints such as latency, thermal limits and functional safety.

Key responsibilities

• Deploy and operate production‑grade ML inference and learning pipelines on Android Automotive OS (AAOS).
• Implement on‑device multimodal large language models, design schemas and safely dispatch calls to local vehicle APIs.
• Integrate models using TensorFlow Lite, ONNX Runtime, or vendor‑specific SDKs.
• Profile and optimise models for strict latency, memory, power and thermal budgets across CPU, GPU and NPU layers.
• Design safety boundaries, guardrails and fallback logic for model outputs, including tool‑call allowlists.
• Interface directly with vehicle signals, sensors and system services via C++ and JNI.

Required profile

• BS, MS or PhD in Computer Science, Electrical Engineering or a related field.
• 3+ years of experience shipping ML inference on embedded, mobile or automotive platforms.
• Strong proficiency in C++ and native Android integration (JNI).
• Demonstrated expertise in model optimisation techniques such as quantisation, pruning and compilation.

Required skills

• C++
• JNI (Java Native Interface)
• TensorFlow Lite
• ONNX Runtime
• Model quantisation, pruning and compilation
• LLM function calling / tool execution
• Android Automotive OS (AAOS) and Android system services
• Profiling and optimisation for CPU, GPU and NPU acceleration
• Design of safety guardrails and fallback mechanisms

What we offer

• Opportunity to work on cutting‑edge on‑device AI for autonomous vehicles.
• Collaborative in‑office environment in Sunnyvale with occasional flexibility for remote work.
• Access to advanced hardware platforms and cross‑functional teams.