RADD Co | Remote (U.S.) | Defense Technology | Acoustic c-UAS 

• Location: Remote (U.S.-based)

• Travel: Up to 25% (flexible)

• Citizenship: U.S. Citizenship required

• Clearance: Ability to obtain a U.S. Security Clearance (active clearance preferred) 

The Mission 

RADD Co is redefining battlefield awareness through advanced acoustic sensing and sensor fusion. We empower warfighters in the world’s most dangerous environments with actionable intelligence—when it matters most. Our systems detect and track real-time aerial threats at the tactical edge using ultra-low-power sensors and fusion devices. 

We are looking for a Machine Learning Engineer who thrives at the intersection of physical signals and resource-constrained hardware. You aren't just building models in a vacuum; you are building the intelligence that allows our hardware to succeed in the mud. 

The Role 

As a Machine Learning Engineer at RADD Co, you will own the technical integrity of our acoustic models, from the moment a sound is digitized to the moment a result is triggered on an edge device. 

• End-to-End Execution: Drive the entire lifecycle: data collection and labeling, EDA, feature engineering, model architecture, training, evaluation, and monitoring. 

• Edge-First Development: Our models aren’t always complex, but they must be brilliant within tight constraints. You will design efficient architectures and strategies to ensure high-performance inference on extremely resource-constrained edge devices. 

• Model Development: Develop and evolve robust models for signal classification and estimation tasks (e.g., distance or orientation) based on acoustic time-series and sensor data. 

• Domain Expansion: Partner with Operations to define and codify our ODD into a structured data ontology. You will ensure our models are balanced across diverse environments and noise sources, stay site-agnostic, and can easily adapt to new target domains. 

• Infrastructure & Tooling: You will be responsible for evolving our ML stack, including the tools needed for data curation/selection, automated model building, cloud-based training, and rigorous automated testing of model performance. 

Required Experience 

Success in this role requires a baseline of "full-lifecycle" ML maturity and experience shipping to physical devices: 

• Depth: 5+ years of experience building and deploying machine learning models. 

• Proficiency: Expert-level proficiency in Python and Keras (or similar). 

• Edge Architecture: Proven experience building efficient model architectures designed for low-power, low-memory environments. Experience with low resource model frameworks and techniques (e.g. TFLite, TensorRT, QaT). 

• Infrastructure Automation: Experience building automated pipelines for model validation, data selection, and experiment tracking. 

• Data Craft: You view data curation and feature engineering as a core engineering discipline, not a chore. You are comfortable working with Operations to bridge the gap between lab assumptions and tactical ground-truth. 

Preferred 

• Signal Processing: Experience designing and implementing real-time filters and frequency-domain features for acoustic or other time-series data. 

• Geospatial Data: Experience working with geospatial data and telemetry for model validation, automated labeling workflows, or system visualization. 

• Estimation: Practical application of state estimation or localization on noisy sensor data (e.g., location, compass or IMU data). 

Why You’re the Right Fit 

You think in systems, not silos. You thrive in small, elite teams where ownership is absolute and there is always a critical mission to achieve. You aren't interested in "tried-and-true" solutions; you are motivated by the opportunity to define a new category of technology and see your work perform in the mud, the wind, and the field. 

Why RADD?

• Build life-saving technology for operators in real-world conflict zones 

• Define a new category in acoustic counter-UAS sensing 

• Own the decision advantage hardware layer 

• Join at the ground floor and shape the company’s future 

• Work on problems where performance matters—and failure is not an option