Edge AI Engineer: Real-Time, Low-Power ML on Devices

Jabil; Seberang Perai; On-site; MYR 120,000 - 180,000; Full time

Job summary

Jabil in Malaysia seeks an experienced AI/ML Engineer to design and optimize edge AI solutions for resource-constrained devices at our Penang location. You will implement inference engines, work with sensor data, and collaborate with hardware teams to select edge platforms.

The role emphasizes quantization, pruning, and distillation for efficient edge deployment, plus building robust MLOps and validation workflows.

Qualifications

• 3+ years of experience in AI/ML with emphasis on embedded/edge computing
• Proficiency in Python and C++
• Experience with TensorFlow Lite, PyTorch Mobile, or similar frameworks
• Knowledge of neural networks, computer vision, and/or natural language processing
• Experience with edge platforms and hardware accelerators

Responsibilities

• Design, develop, and optimize AI/ML models for resource-constrained edge devices
• Implement efficient inference engines and real-time data pipelines at the edge
• Work with sensor data to develop robust AI applications
• Collaborate with hardware engineers to select edge computing platforms
• Optimize model performance for power, latency, and memory on target hardware
• Develop MLOps strategies for CI/CD and monitoring of edge AI models
• Conduct performance benchmarking and validation of edge AI solutions
• Stay updated on edge computing, AI hardware, and ML advances
• Provide technical guidance to cross-functional teams
• Document designs, architectures, and implementation details thoroughly

Skills

Python

C++

Embedded systems

Edge AI

RTOS

Education

Bachelor's or Master's in Computer Science, Electrical Engineering, Robotics, or related field

Tools

TensorFlow Lite

PyTorch Mobile

HailoRT

NVIDIA Jetson

Google Coral

Job description

Jabil in Malaysia seeks an experienced AI/ML Engineer to design and optimize edge AI solutions for resource-constrained devices at our Penang location. You will implement inference engines, work with sensor data, and collaborate with hardware teams to select edge platforms.

The role emphasizes quantization, pruning, and distillation for efficient edge deployment, plus building robust MLOps and validation workflows.