> Markdown version of [/jobs/ext/4608311-staff-audio-machine-learning-engineer](https://www.wearedevelopers.com/jobs/ext/4608311-staff-audio-machine-learning-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff Audio Machine Learning Engineer

- **Company:** Boston Dynamics
- **Location:** United States
- **Experience:** Expert
- **Salary:** $180,000.0 - $220,000.0
- **Contract:** Permanent contract
- **Skills:** Data Analysis, Computer Vision, C++ (Programming Language), Python (Programming Language), Machine Learning, NumPy, SciPy, Data Streaming, TypeScript, Web Services, Pytorch, Large Language Models, Scikit Learn, Machine Learning Operations, Feature Extraction
- **Published:** November 6, 2026
- **Apply:** https://startup.jobs/senior-staff-audio-machine-learning-engineer-boston-dynamics-inc-10697086

## About the Role

* Experience: 7+ years of deep practical expertise in audio feature extraction, audio fingerprinting (e.g., Shazam, DMCA enforcement) and segmentation (e.g., DCASE), machine learning applied to audio data (beamformed and raw), preferably in industrial environments or another domain with similar problems, for the purposes of anomaly detection.

Technical Skills & Hardware

 * Languages & Core Tooling: Advanced proficiency in Python and C++, with mastery of numerical and scientific stacks (e.g., NumPy, SciPy, scikit-learn, PyTorch).
 * Acoustic Processing: Expertise in time domain and frequency domain data analysis.
 * Array Processing: Expertise in multi-channel array processing, including beamforming (Delay-and-Sum, MVDR, null-steering), Direction of Arrival (DoA) estimation, and synthetic aperture techniques.
 * Machine Learning & Modeling Paradigms: Expertise in unsupervised and supervised classification architectures for anomaly detection in real-world conditions.

Bonus Points

 * Hands-on experience in cross-modal fusion (combining audio representations with computer vision, thermal imaging, or multimodal foundation models/VLMs).
 * Background in rotating machinery health monitoring (bearings, gearboxes, pumps) and familiarity with mechanical vibration/acoustic failure standards.
 * Familiarity with TypeScript/modern web services for integrating your work into Orbit, our fleet management software.

We are interested in every qualified candidate who is eligible to work in the United States. However, we are not able to sponsor visas for this position.

## Description

* Acoustic ML & DSP Ownership (Core Focus): Design, refine, and scale digital signal processing and machine learning pipelines for our Acoustic Change Detection (ACD) system.
 * Anomaly Detection & Failure Classification: Lead the improvement and modernization of our acoustic detection stack-transitioning from unsupervised models (e.g., BGMM) to state-of-the-art anomaly architectures, and architecting our end-to-end supervised multimodal pipelines for automated fault diagnosis.
 * Multimodal Integration & Prescriptive Maintenance: Partner with the broader Spot Apps organization to integrate acoustic insights with visual, thermal, and VLM/LLM data streams into unified machine health indicators, delivering both clear mechanical diagnoses and recommended corrective actions to plant operators.
 * Industrial Deployment & Verification: Benchmark, optimize, ship, monitor, and continuously improve our solution for our industrial customers.