Senior Embedded Edge AI Systems Architect

About Asiacruit

At Asiacruit, we connect top talent with forward-thinking organizations across industries. Our mission is to help businesses grow through smart, strategic, and people-focused solutions. We support companies by providing high-quality talent for local and global markets.

Position Overview

We are looking for a Senior Embedded Edge AI Systems Architect to design and optimize AI computing systems for advanced robotics and edge applications.

In this role, you will deploy AI models on embedded computing platforms, optimize inference performance, integrate sensors and software systems, and ensure reliable operation under hardware, power, and thermal constraints.

Key Responsibilities

- Design embedded AI computing architectures using NVIDIA Jetson platforms, including Jetson AGX Orin.
- Optimize AI inference performance using CUDA, TensorRT, TensorRT-LLM, and model quantization techniques.
- Deploy quantized neural network models on embedded and robotic hardware.
- Develop high-performance communication pipelines between AI inference systems and robotics middleware, including ROS 2.
- Implement zero-copy data transfer and shared-memory inter-process communication.
- Integrate and synchronize data from 3D LiDAR, RGB-D cameras, stereo cameras, and IMUs.
- Implement sensor synchronization using IEEE 1588 Precision Time Protocol (PTP) and hardware timestamping.
- Optimize system power consumption, thermal performance, and computing efficiency.
- Implement hardware watchdogs and reliability mechanisms for embedded systems.
- Collaborate with AI, robotics, and hardware engineering teams to validate system performance on physical platforms.

Qualifications

- Bachelor's or Master's degree in Computer Engineering, Electrical Engineering, Computer Science, or a related field.
- At least 5 years of embedded systems experience, with substantial hands-on experience in embedded AI or edge computing.
- Proven experience deploying AI models on NVIDIA Jetson platforms or comparable embedded AI hardware.
- Strong proficiency in C++ and CUDA programming.
- Hands-on experience with embedded Linux and NVIDIA Jetson Linux (L4T).
- Experience optimizing AI inference using TensorRT. TensorRT-LLM experience is highly relevant.
- Understanding of neural network quantization techniques, including INT8, INT4, or FP8.
- Experience with shared memory, zero-copy data pipelines, or high-performance inter-process communication.
- Knowledge of ROS 2 integration and real-time sensor data processing.
- Familiarity with IEEE 1588 PTP, hardware timestamping, and sensor synchronization.
- Understanding of embedded hardware power management, thermal optimization, and system reliability.

Why Join?

- Work on advanced AI and robotics engineering challenges.
- Contribute to deploying AI models on real-world embedded computing platforms.
- Collaborate with multidisciplinary teams across AI software, robotics, and hardware engineering.
- Take ownership of system architecture, performance optimization, and hardware integration.