General Summary:
We are seeking a highly skilled Machine Learning Engineer to join Qualcomm Multimedia Audio Systems and R&D group. The successful candidate will utilize existing trained machine learning models for a variety of audio and voice technologies, including speech enhancement, acoustic echo cancellation, noise suppression, handsfree voice calls, zonal voice calls, voice control by voice commands, keyword spotting, audio context/scene detection, source separation, and fully supervised speaker diarization. The role involves quantizing these models as needed and implementing them on Qualcomm SoCs for optimized on-device inference. We are looking for a candidate who is passionate about pushing the boundaries of audio and voice technology through innovative machine learning solutions.
Responsibilities:
The candidate will be expected to work with a team of engineers to prototype and productize Voice AI Models for Automotive
Develop, Train, and Optimize Voice AI models for efficient offload to NPU, GPU and CPU
Perform Model evaluation and performance analysis for different architectures and multiple open-source models
Work closely with other R&D and Systems team for system integration, use case validation and commercialization support
Utilize trained machine learning models for speech enhancement, acoustic echo cancellation, and noise suppression.
Develop and implement solutions for handsfree voice calls, zonal voice calls, and voice control by voice commands.
Work on keyword spotting and audio context/scene detection.
Perform source separation and fully supervised speaker diarization.
Quantize models where necessary and implement them on Qualcomm SoCs for optimized on-device inference.
Requirements:
Strong programming skills in C/C++, Python, Matlab
Experience working on Audio Signal processing algorithms and solutions
Experience working on Audio, Speech enhancement DNN models for Noise Suppression, Echo Cancellation
Basic knowledge in advanced adaptive signal processing techniques, multi-rate signal processing, adaptive beamforming, and distributed microphone-based signal processing for tracking and speech enhancement.
Familiarity with audio/voice signals and the ability to analyze them using tools like audition.
Knowledge of any ML frameworks pytorch, tensorflow, ONNX..
Familiarity with recent trends in machine learning (diffusion models, U-Nets, Transformer, BERT, BART, etc.) and traditional statistical modeling/feature extraction techniques
Knowledge of Model quantization and compression techniques
Expertise in developing and debugging software on embedded platforms
Knowledge of software design patterns and multi-threaded programming, Eg POSIX or PTHREADS
Knowledge of computer architecture, operating systems, data structures, and basic algorithms
Knowledge of fixed-point coding
Experience working on any AI HW accelerator NPU or GPU is a plus
Experience working on any DSP architecture and framework is a plus
Educational Qualification:
Bachelor's/Master’s/PhD degree in Engineering, Electronics and communication, Computer Science or related filed.
2+ years of Audio Systems engineering or Audio Signal Processing modules or ML Model development or related work experience.
Minimum Qualifications:
Applicants: Qualcomm is an equal opportunity employer. If you are an individual with a disability and need an accommodation during the application/hiring process, rest assured that Qualcomm is committed to providing an accessible process. You may e-mail disability-accomodations@qualcomm.com or call Qualcomm's toll-free number found here. Upon request, Qualcomm will provide reasonable accommodations to support individuals with disabilities to be able participate in the hiring process. Qualcomm is also committed to making our workplace accessible for individuals with disabilities. (Keep in mind that this email address is used to provide reasonable accommodations for individuals with disabilities. We will not respond here to requests for updates on applications or resume inquiries).
Qualcomm expects its employees to abide by all applicable policies and procedures, including but not limited to security and other requirements regarding protection of Company confidential information and other confidential and/or proprietary information, to the extent those requirements are permissible under applicable law.
To all Staffing and Recruiting Agencies:Our Careers Site is only for individuals seeking a job at Qualcomm. Staffing and recruiting agencies and individuals being represented by an agency are not authorized to use this site or to submit profiles, applications or resumes, and any such submissions will be considered unsolicited. Qualcomm does not accept unsolicited resumes or applications from agencies. Please do not forward resumes to our jobs alias, Qualcomm employees or any other company location. Qualcomm is not responsible for any fees related to unsolicited resumes/applications.
If you would like more information about this role, please contact Qualcomm Careers.