Edge AI Audio ML Intern

Syntiant; Redwood City (CA); Hybrid; USD 42,000 - 62,000; Full time

Job summary

Syntiant Corp. is seeking a Machine Learning Intern to join the Algorithms team. You will help build, evaluate, and optimize KWS and AED models running on ultra-low-power edge hardware, collaborating with ML, DSP, and hardware engineers.

The role involves data curation, training, and evaluation under memory and power constraints, with exposure to quantization and efficient architectures. Internships may lead to impactful edge AI deployments.

Qualifications

• Pursuing or completed Bachelors or Masters in CS/EE/ML with hands-on DL for audio (coursework, research, or project).
• Proficiency in Python and a DL framework (TensorFlow/Keras preferred; PyTorch acceptable).
• Familiarity with audio signal processing fundamentals (spectrograms, mel filterbanks, feature extraction).
• Understanding ML evaluation concepts (precision/recall, ROC/DET, confusion analysis).
• Exposure to model efficiency concepts (quantization, parameter budgets, edge constraints) is a plus.

Responsibilities

• Support development and evaluation of KWS and AED models and architectures.
• Assist with audio pipeline and feature extraction work; diagnose training/eval issues.
• Help design and prune CNN architectures to fit hardware constraints.
• Build diagnostic tooling for FA analysis and visualization to understand model behavior.
• Contribute to data augmentation and hard-negative mining for robust detection.
• Plan and track data collection, maintaining inventories and logs.
• Analyze experiment results and summarize findings for the team.
• Collaborate with ML, DSP, and hardware engineers to validate models on hardware.

Skills

Python

Deep learning for audio

CNNs/RNNs on audio data

Edge ML constraints

Data analysis

Education

Bachelor's or Master's in CS/EE/ML

Tools

TensorFlow/Keras

PyTorch

Librosa

Job description

Syntiant Corp. is seeking a Machine Learning Intern to join the Algorithms team. You will help build, evaluate, and optimize KWS and AED models running on ultra-low-power edge hardware, collaborating with ML, DSP, and hardware engineers.

The role involves data curation, training, and evaluation under memory and power constraints, with exposure to quantization and efficient architectures. Internships may lead to impactful edge AI deployments.