Embedded machine learning model deployment

You know the moment. It’s the first notes of that song you love, the intro to your favorite movie, or simply the sound of someone you love saying “hello.” It’s in these moments that sound matters most.

At Bose, we believe sound is the most powerful force on earth. We’ve dedicated ourselves to improving it for more than 60 years. And we’re passionate down to our bones about making whatever you’re listening to a little more magical.

The Engineering team at Bose is a thriving, passionate, deeply skilled team of professionals from a broad range of disciplines and experiences, who share a common goal—to create products that provide transformative sound experiences.

Job Description

Timeframe: June 1 – August 21, 2026 and able to work in a hybrid work environment.

THE ROLE

We’re looking for an Embedded Machine Learning Intern to join the Corporate Research Team in Model Compression & Deployment. In this role, you will..

• Design and implement compiler-level optimizations and mapping strategies to efficiently deploy deep learning models on embedded platforms with neural network accelerators.
• Develop and optimize sparse kernel implementations tailored to target hardware, focusing on performance, memory efficiency, and energy savings.
• Build and evaluate machine learning model mappers that translate high-level models into hardware-executable formats.
• Collaborate cross-functionally to integrate ML workloads into embedded systems, ensuring end-to-end functionality.
• Stay up-to-date and experiment with the latest research in sparse computation, model optimization, and deployment frameworks.
  
  

Requirements

To be successful in this role, you should be/have:

• Currently pursuing an M.S. or Ph.D. in Computer Science, Electrical Engineering, Computer Engineering, or a related field.
• Solid programming background with 3+ years of experience in C/C++ and Python.
• Strong experience with machine learning frameworks (e.g., PyTorch, TensorFlow) and compiler stacks (e.g., TVM, MLIR, XLA).
• Hands-on experience in at least one of the following:
  • Sparse kernel development (CPU, GPU, DSP, or NPU)
  • Model-to-hardware mapping and deployment
  • Embedded system programming and runtime optimization
• Familiarity with techniques such as pruning, quantization, and graph-level model transformation.
• Strong problem-solving and system-level thinking abilities.
  
  

Preferred Qualifications

• Proven experience through internships, research, or projects involving ML compiler optimization or hardware-software co-design.
• Knowledge of ML deployment on resource-constrained devices such as microcontrollers or DSPs.
• Familiarity with digital signal processing and audio-based ML applications.
• Publications or open-source contributions related to model optimization, hardware-aware ML, or embedded AI. (e.g., ICLR, ISCA, ICASSP, INTERSPEECH)
  
  

Bose is an equal opportunity employer. We evaluate qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity, genetic information, national origin, age, disability, veteran status, or any other legally protected characteristics. The EEOC’s “Know Your Rights: Workplace discrimination is illegal” Poster is available here: Bose is committed to providing reasonable accommodations to individuals with disabilities. If you require reasonable accommodation in completing this application, interviewing, completing any pre-employment testing, or otherwise participating in the employee selection process, please direct your inquiries to [email protected]. Please include "Application Accommodation Request" in the subject of the email.

Our goal is to create an atmosphere where every candidate feels supported and empowered in the interviewing process. Diversity and inclusion are integral to our success, and we believe that providing reasonable accommodation is not only a legal obligation but also a fundamental aspect of our commitment to being an employer of choice. We recognize that individuals may have different needs and requirements based on their abilities, and we provide reasonable accommodations to ensure ideal conditions are met during the application process.