AI Engineer – Sound Analysis and Pattern Recognition at Lytup Power Systems Inc

Position Overview:

• We are seeking a talented and experienced AI Engineer specializing in sound analysis and pattern recognition. In this role, you will develop algorithms and AI models that analyze audio inputs in real-time, filter background noise, and identify unique sound patterns. You’ll work closely with our cross-functional engineering team to design and implement efficient, high-performance solutions for an embedded system.

Key Responsibilities:

• Develop and optimize algorithms for sound recognition and real-time audio processing.
• Design and train AI models for pattern recognition in audio signals, focusing on precision and low-latency performance.
• Implement noise filtering and audio pre-processing techniques to enhance the accuracy of sound identification.
• Collaborate with firmware engineers to integrate AI models into an embedded system for efficient, low-power operation.
• Conduct testing and validation to ensure accuracy and reliability in varying environmental conditions.
• Continuously improve AI models by refining datasets and enhancing detection accuracy.
• Provide technical guidance on AI and machine learning best practices within the team.

Required Skills and Experience:

• Experience in AI and Machine Learning: Strong background in developing AI models, particularly for audio/sound analysis and pattern recognition.
• Audio Signal Processing: Proficiency in digital signal processing (DSP), including noise reduction, feature extraction, and frequency analysis.
• Embedded Systems: Familiarity with deploying AI models on embedded systems with a focus on optimizing for limited resources and low power consumption.
• Programming Languages: Proficient in Python and C/C++ for model development and deployment; experience with TensorFlow Lite, PyTorch Mobile, or similar tools for lightweight AI.
• Algorithm Development: Ability to design and implement custom algorithms for identifying specific patterns in audio data.
• Machine Learning Frameworks: Experience with ML frameworks like TensorFlow, Keras, or PyTorch, especially for audio classification tasks.
• Data Management: Skills in creating and managing large, labeled audio datasets for training and testing models.
• Problem-Solving Mindset: Strong analytical and critical thinking skills, with the ability to translate abstract requirements into practical, efficient AI solutions.

Preferred Qualifications:

• Experience in bioacoustics or related fields focusing on natural sound recognition.
• Knowledge of low-power hardware platforms (e.g., ARM Cortex-M, DSP chips) and microcontroller-based AI deployment.
• Familiarity with FFT (Fast Fourier Transform) and other spectral analysis techniques.
• Experience with real-time processing in challenging environmental conditions.