General Summary:
Qualcomms Audio Systems team is seeking a talented and highly motivated engineer specialized in the implementation of Voice AI and Audio solutions. You will work with a team to prototype, optimize, and productize state-of-the-art ML models, ensuring efficient deployment on snapdragon platforms
Responsibilities:
- Develop, optimize, and deploy Voice AI and audio ML models for audio applications, with a focus on inference efficiency across NPUs, GPUs, and CPUs.
- Perform model evaluation, quantization, and compression to enable fast, robust inference on embedded hardware.
- Analyze and compare model architectures (such as Diffusion Models, U-Nets, Transformers, BERT, BART, etc.) for use in audio applications.
- Collaborate with cross-functional R&D, systems, and integration teams for system use case verification and commercialization support.
- Contribute to the design and software implementation of audio ML models in embedded C/C++ and Python.
- Evaluate system performance, debug, and optimize for performance and robustness.
- Participate in industry trends, benchmarking and performance analysis of various Model architecture, and bring up-to-date architectural or technical innovations to the team.
Requirements:
- Strong programming skills in C/C++, Python.
- Experience with audio processing and embedded solutions.
- Hands-on experience working with audio framework and audio solutions on any platform
- Familiarity with ML frameworks (PyTorch, TensorFlow, ONNX, etc.).
- Knowledge of model quantization and compression techniques, and experience optimizing inference and deployment on embedded hardware.
- Strong understanding of ML model architectures such as, CNNs, RNNs, Transformers, U-Nets, and statistical modeling techniques.
- Understanding of DSP or Microcontroller architectures and frameworks
- Experience developing and debugging software on embedded platforms; familiarity with software design patterns, multi-threaded programming (e.g., POSIX, PTHREADS), and fixed-point coding.
- Excellent verbal and written communication skills; ability to work independently and as a team player in geographically dispersed, multidisciplinary teams.
- Proven ability to work in a dynamic, multi-tasked environment quick learner, self-motivated, and results-driven.
Minimum Qualifications:
Bachelors, Masters or PhD in Computer Science, Electronics and Communication, Electrical Engineering, or a related field (or equivalent work experience).
Preferred Qualifications:
- Experience working with Qualcomm AI HW accelerators (NPUs) and Qualcomm SDKs
- Knowledge of Qualcomm ML framework QNN, platforms and tools
Keywords: Audio ML Models, RNNs, Audio dataset, Inference Optimization, ML model Quantization, Quantization aware, post training quantization, Model optimization
Minimum Qualifications:

Keyskills: machine learning python software design ai electrical engineering audio processing r tensorflow model evaluation audio systems pytorch debugging statistical modeling systems engineering programming performance analysis architecture