Acoustic Machine Learning Engineer

Senior Applied Acoustic Machine Learning Engineer – Help Power Autonomous Defense Systems with Real-World Perception!

Austin, TX | On-site

An early-stage, well-funded defense technology startup is building autonomous systems designed to detect and respond to fast-moving aerial threats in complex outdoor environments. At the core of this mission is real-time perception, where advanced machine learning meets rugged hardware deployed in the field. The team is seeking a Senior Applied Acoustic Machine Learning Engineer to lead development of intelligent audio-based detection and classification systems that perform reliably under extreme noise, weather, and domain variability.

In this role, you will transform raw acoustic data into high-confidence real-world decision-making. You’ll bridge modern ML with signal processing fundamentals, own model performance end-to-end, and deploy edge-ready inference systems that operate under tight latency and reliability constraints. If you enjoy building perception systems that actually ship, operate in the wild, and directly power autonomous platforms, this is a high-impact opportunity at the ground floor of a fast-scaling defense startup.

We are a venture-backed robotics and autonomy company developing intelligent defense platforms designed to operate in real-world, high-stakes environments. Our systems combine advanced sensing, machine learning, and autonomous decision-making to deliver field-ready capability rather than lab prototypes. With strong early funding and rapid technical progress, our team is focused on turning breakthrough perception technology into deployable hardware that protects critical assets and people.

• Design and train machine learning models for acoustic detection, classification, and target tracking in outdoor environments
• Develop hybrid approaches combining multichannel audio features, beamforming outputs, and modern neural architectures
• Build and maintain data pipelines including labeling strategies, evaluation frameworks, and continuous model improvement loops
• Implement robustness strategies to reduce false positives caused by wind, weather, reflections, and environmental variability
• Deploy optimized inference pipelines for edge hardware with strict latency and performance requirements
• Integrate diagnostics and monitoring to support real-time operational performance
• Partner with hardware engineers and signal processing specialists to align sensor calibration, data quality, and system metrics
• Perform deep error analysis and iterative model refinement to drive real-world reliability

• 5+ years of applied machine learning experience working with audio, sensor data, or similarly noisy real-world signals
• Demonstrated experience deploying ML models into real operational environments with measurable performance outcomes
• Strong proficiency in Python and modern ML frameworks
• Solid understanding of signal fundamentals such as noise sources, synchronization, and sensor behavior
• Experience designing reproducible experiments, evaluation pipelines, and systematic model improvement processes
• Ability to own projects end-to-end from data through deployment

• Edge inference optimization including quantization, runtime acceleration, or hardware-aware deployment
• Experience with weakly supervised learning, domain adaptation, or robustness techniques
• Work on multi-sensor fusion or temporal modeling systems
• Familiarity with low-latency embedded or real-time systems
• Passion for robotics, autonomy, or hands-on technical projects outside of work

• Build perception systems that directly power real autonomous platforms
• High ownership over core machine learning architecture and performance
• Work closely with hardware and autonomy teams in a deeply technical environment
• Opportunity to shape foundational technology at a seed-stage company
• Fast iteration cycles with real-world deployment and feedback
• Strong growth trajectory as the company scales programs and platforms
• Early-stage equity

$140,000 - $220,000