Infineon Technologies

Principal Engineer for Edge AI Software_7593

Infineon Technologies
Apply
3 months ago
Beijing, ChinaStaff+
H1B Sponsor

Responsibilities

  • Design and deploy AI/ML models on embedded and edge devices such as MCUs and AI-enabled SoCs.
  • Integrate AI inference pipelines into embedded software stacks and real-time operating system environments.
  • Optimize models and runtime performance for latency, memory usage, power efficiency, and reliability.
  • Develop and maintain data-processing pipelines for feature extraction, buffering, and synchronous inference.
  • Collaborate with firmware, hardware, and algorithm engineers on system integration.
  • Troubleshoot deployment issues involving timing, memory allocation, data flow, and runtime behavior.
  • Support maintainable deployment processes through version control, reproducibility, and traceability.
  • Evaluate and apply tools and frameworks for model conversion, quantization, and on-device inference.

Requirements

  • Bachelor’s or master’s degree in Computer Science, Computer Engineering, Electrical Engineering, Embedded Systems, or a related field.
  • Strong C/C++ programming skills for embedded software development.
  • Solid understanding of RTOS concepts, task scheduling, interrupts, DMA, synchronization, and real-time constraints.
  • Experience deploying AI/ML models to edge devices using TensorFlow Lite Micro, ExecuTorch, CMSIS-NN, or similar toolchains.
  • Understanding of model quantization, memory optimization, and performance tuning on constrained hardware.
  • Familiarity with sensor or signal-processing workflows involving time-series data such as vibration, audio, current, or power signals.
  • Strong debugging and problem-solving skills across software, model, and hardware integration layers.
  • Ability to support the complete deployment lifecycle from prototype through production.
  • Experience with MCU-based AI acceleration or related edge-inference platforms is preferred.
  • Familiarity with FreeRTOS, RT-Thread, or similar embedded operating systems is preferred.
  • Experience in IoT, industrial, or consumer-electronics applications is preferred.
  • Knowledge of model lifecycle management, firmware release processes, and production validation is preferred.
  • Experience using Python-based ML tools for model preparation, evaluation, and conversion is preferred.

Tech Stack

Infineon Technologies

About Infineon Technologies

10,000+ employees

Semiconductors are crucial to solve the energy challenges of our time and shape the digital transformation. This is why Infineon is committed to actively driving decarbonization and digitalization. As a global semiconductor leader in power systems and IoT, we enable game-changing solutions for green and efficient energy, clean and safe mobility, as well as smart and secure IoT. We make life easier, safer, and greener. Together with our customers and partners. For a better tomorrow. Together, with more than 58,000 people from over 100 countries, we are not just shaping the future. We are redefining it. We engineer innovative products, while caring for our people and empowering them to reach ambitious goals. We offer work-life balance, long term growth and a supportive environment where individuality is celebrated. #WeAreIn for driving decarbonization and digitalization. Are you in?

Contact me