About the job
Location: Onsite — Austin, TX
Employment Type: Full-Time
About Us
At 9-mothers, we are an innovative startup dedicated to developing autonomous machines for defense applications. Our flagship product is engineered to neutralize small, high-speed FPV suicide drones. We pride ourselves on transforming state-of-the-art machine learning technologies into reliable, field-ready solutions that ensure superior perception and decision-making capabilities.
Position Overview
We are in search of a Senior Applied Acoustic Machine Learning Engineer who will leverage machine learning techniques to enhance our systems' ability to detect, classify, and track acoustic targets accurately. This role will entail integrating traditional Digital Signal Processing (DSP) methodologies with modern machine learning practices to enable our interceptors to effectively identify threats amidst challenging environmental conditions and outdoor noise.
Key Responsibilities
Develop Hybrid Models: Create sophisticated models that integrate beamformed channels with multichannel features to ensure robust target detection and classification.
Manage the Data Lifecycle: Establish labeling strategies, construct training and evaluation pipelines, and implement hard-negative mining techniques to adapt to a variety of outdoor scenarios.
Enhance System Robustness: Proactively reduce false alarm rates caused by environmental factors such as wind, rain, and reflections across diverse terrains and sensor configurations.
Implement Edge Inference: Successfully deploy models to edge computing environments with stringent latency requirements, incorporating diagnostics to ensure real-time operability.
Collaborate Across Teams: Work closely with Hardware and DSP teams to ensure synchronization of data, calibration, and performance metrics.
Qualifications
Experience: Proven track record in deploying machine learning solutions for audio or similarly noisy sensors, with demonstrable operational metrics such as precision, recall, and false alarm rates.
Engineering Discipline: Strong commitment to rigorous machine learning engineering practices, including reproducible experimentation, comprehensive ablation studies, and systematic error analysis.
Technical Foundations: Solid understanding of microphone array principles (Signal-to-Noise Ratio, aliasing, synchronization) sufficient to troubleshoot issues and design effective tests.
Programming Skills: Proficiency in programming languages relevant to ML and DSP, with experience in developing scalable algorithms.

