Edge AI Engineer — Audio DSP on Devices

Bose Corporation; Framingham (MA); On-site; USD 141,000 - 194,000; Full time

Benefits offered by this job

Bonus programs

Health and welfare benefits

401(k) plan

Employee discount

Job summary

Bose Corporation is seeking an Edge AI ML Engineer to develop, optimize, and deploy ML models for audio and multimodal intelligence on real devices. This role sits at the junction of ML modeling, DSP, and embedded systems to transform research concepts into efficient, production-ready algorithms.

You will collaborate with ML researchers, firmware engineers, and hardware teams to ensure models meet real-world constraints such as latency, memory, and power, enabling edge deployment across Bose

Qualifications

• Strong proficiency in C/C++ for embedded systems.
• Strong experience developing and evaluating machine learning models, preferably for audio, speech, or other time-series sensor data.
• Experience optimizing ML models for edge, embedded, or resource-constrained environments.
• Proficiency in Python for model development, experimentation, evaluation, and tooling.

Responsibilities

• ML Modeling & Algorithm Development: identify DSP/ML opportunities considering device constraints and hardware capabilities.
• Embedded / On-Device Engineering: deploy models to device runtimes and hardware accelerators; optimize memory and latency.
• Platform & Performance Engineering: profile and optimize across MCUs, DSPs, NPUs, and toolchains; integrate with on-device ML runtimes.

Skills

C/C++

Edge ML

ML modeling

Python

Education

Master’s or Ph.D. in CS/EE/ML or related

Tools

MLIR

Glow

ExecuTorch

Job description

Bose Corporation is seeking an Edge AI ML Engineer to develop, optimize, and deploy ML models for audio and multimodal intelligence on real devices. This role sits at the junction of ML modeling, DSP, and embedded systems to transform research concepts into efficient, production-ready algorithms.

You will collaborate with ML researchers, firmware engineers, and hardware teams to ensure models meet real-world constraints such as latency, memory, and power, enabling edge deployment across Bose