Lead Applied Scientist - Signal Processing & Machine Learning- AquaEye

About this role

AquaEye is a fast-growing technology company transforming the global water rescue industry through rapid-deployment intelligent sonar solutions. Our flagship product, AquaEye, is a handheld sonar device designed to help first responders locate drowning victims faster and more effectively.
As we continue to advance AquaEye's detection capabilities and develop new products, we are looking for a hands-on Applied Scientist with deep experience working with complex real-world sensor data, signal processing, acoustics, sound engineering, sonar, or related scientific data.
This role sits at the intersection of signal processing, data science, machine learning and embedded product development.
We are particularly interested in someone fascinated by the data underneath the algorithm: understanding what our sonar signals contain, identifying and extracting meaningful information from noisy real-world data, determining which features matter, and using that understanding to develop effective detection methodologies and machine learning solutions.
You do not need to come from the water-rescue industry or have worked specifically with AquaEye's technology. Experience interpreting complex signals in fields such as sonar, acoustics, audio/sound engineering, radar, medical devices, telecommunications, geophysics, remote sensing, robotics, industrial sensing or other sensor-based systems may be highly transferable.
This is a highly hands-on role within a small, collaborative product-development team. You will work closely with hardware, embedded software, engineering and product leadership to help determine the next generation of AquaEye's core detection technology.
Job Responsibilities:
Signal Processing & Applied Data Science

• Lead the exploration and interpretation of raw sonar and sensor data to understand the information contained within the signal.

• Design, evaluate and improve signal-processing methodologies used to extract meaningful features from complex and noisy real-world data.

• Investigate signal characteristics across different environments and operating conditions to understand sources of noise, variability and performance degradation.

• Apply techniques such as filtering, spectral analysis, time- and frequency-domain analysis, feature extraction and Fourier transforms, where appropriate.

• Determine which characteristics of the underlying data are most useful for detection and classification.

• Develop experimental approaches to distinguish meaningful signal from environmental noise and other confounding factors.

• Work closely with hardware and embedded engineering teams to understand how sensor design, device configuration and operating conditions influence data quality.
Machine Learning & Algorithm Development

• Design and develop detection methodologies using the most appropriate combination of signal processing, statistical methods, machine learning and algorithmic approaches.

• Develop, train, validate and deploy machine learning models where ML provides meaningful value.

• Evaluate both simple and complex approaches rather than assuming a particular ML architecture is the answer.

• Convert scientific and algorithmic concepts into production-quality code for embedded and/or cloud environments.

• Define meaningful performance metrics, with particular attention to false positives, false negatives, generalization and performance across different operating environments.

• Continually experiment with and evaluate new approaches to improve detection performance.

• Optimize algorithms and models for performance within embedded hardware constraints.
Data Strategy & Field Experimentation

• Help define what data AquaEye needs to collect to improve its detection capabilities.

• Design experiments and field-data collection initiatives that test specific hypotheses and address gaps within existing datasets.

• Establish methodologies for data cleaning, preprocessing, labelling, quality assurance and validation.

• Identify biases, gaps and underrepresented operating conditions within existing datasets.

• Build datasets that represent the range of real-world environments in which AquaEye is deployed.

• Develop rigorous approaches for evaluating whether improvements observed during development generalize to real-world field conditions.
Product Development & Technical Direction

• Work alongside Product, Hardware, Embedded Software and executive leadership to define the technical roadmap for AquaEye's detection capabilities.

• Translate scientific findings into practical product improvements.

• Help determine when challenges should be addressed through better data, signal processing, algorithm development, machine learning, hardware changes, or a combination of approaches.

• Participate in field testing, customer trials and product validation.

• Communicate complex scientific and technical concepts clearly to both technical and non-technical stakeholders.

• Contribute to the longer-term development of AquaEye's data science and machine learning capabilities.
Technical Leadership & Team Development

• Serve as a senior technical resource within the product-development team.

• Provide technical guidance and mentorship as AquaEye's data science and ML capabilities grow.

• Establish rigorous scientific and engineering practices around experimentation, validation, documentation and reproducibility.

• Conduct technical reviews and encourage knowledge sharing across engineering disciplines.

• Help define the skills and capabilities required as the future data science/ML team expands.

Requirements

• Bachelor's, Master's or PhD in Engineering, Computer Science, Mathematics, Physics, Acoustics, Signal Processing, Data Science, or another relevant quantitative discipline.

• Approximately 5+ years of relevant industry, applied research or product-development experience.

• Demonstrated experience working directly with raw signals, sensor data or other complex physical-world…