Job Description

Responsibilities:

• Develop and optimize Embedded ML inference engines for microcontrollers.
• Train and fine-tune machine learning models using LLM, TensorFlow and/or PyTorch to be deployed on resource-constrained devices.
• Implement and experiment with techniques to improve model performance on low-power and memory-limited devices.
• Collaborate with cross-functional teams to integrate ML solutions into embedded systems.
• Conduct research on new machine learning techniques and tools specifically for Embedded ML applications.
• Optimize machine learning algorithms to meet the performance and resource constraints of embedded systems.
• Stay up-to-date with the latest advancements in Embedded ML by reading and interpreting technical articles and research papers.

Requirements:

• Master’s degree in Computer Science, Electrical Engineering, or a related field.
• Strong experience with LLM, TensorFlow and/or PyTorch for model training and deployment.
• Proficiency in programming languages such as C, C++, and Python.
• Extensive experience in embedded software development and machine learning.
• Excellent programming skills in at least one of the following: C, C++, or Python.
• Proven ability to read and understand technical articles and research papers in English.
• Strong problem-solving skills and attention to detail.
• Good communication skills and the ability to work collaboratively in a team environment.
• Preferred Qualifications:
• Proven experience with deploying machine learning models to embedded devices, specifically for Embedded ML applications.
• Familiarity with embedded systems, microcontrollers, and real-time operating systems (RTOS).
• Deep understanding of software development life cycle and best practices for embedded systems.
• Previous experience in a full-time role or significant project in a related field.
• Expertise in optimization techniques for low-power and low-latency machine learning models.

More information about NXP in Greater China...

#LI-d6f4