Applied Machine Learning Engineer - Austin

Only for registered members Austin, United States

2 days ago

$90,000 - $155,000 (USD) per year *

* This salary range is an estimation made by beBee

Location: Onsite — Austin, TX · Employment Type: Full-Time · Job Title: Senior Applied Acoustic ML Engineer · Company Overview · We are a funded startup building autonomous machines for defense markets. Our first product is designed to counter small, fast FPV suicide drones. Our ...

Job description

Location: Onsite — Austin, TX

Employment Type: Full-Time

Job Title: Senior Applied Acoustic ML Engineer

Company Overview

We are a funded startup building autonomous machines for defense markets. Our first product is designed to counter small, fast FPV suicide drones. Our robots require world-class perception and decision-making. We turn cutting-edge machine learning into field-ready capability.

Position Summary

We are seeking a Senior Applied Acoustic ML Engineer to use machine learning to make our systems reliably detect, classify, and track acoustic targets. You will bridge the gap between traditional DSP and modern ML, ensuring our interceptors can identify threats under extreme domain shift and outdoor noise.

Essential Duties

Build Hybrid Approaches: Develop models that combine beamformed channels and multichannel features for robust detection and classification.
Own the Data Loop: Define labeling strategies, build training/eval pipelines, and implement hard-negative mining to handle diverse outdoor conditions.
Ensure Robustness: Directly reduce false alarms caused by wind, rain, and reflections across different terrains and sensor units.
Ship Edge Inference: Deploy models to edge runtimes with strict latency constraints, integrating diagnostics so the system is operable in real time.
Cross-Functional Collaboration: Work closely with Hardware and DSP teams to align data, calibration, and performance metrics.

Requirements

Experience: You have shipped ML for audio (or similar noisy sensors) into real usage with measurable operational metrics (precision/recall, false alarms).
Engineering Rigor: Disciplined approach to ML engineering, including reproducible experiments, deep ablations, and systematic error analysis.
Foundations: Practical understanding of mic-array fundamentals (SNR, aliasing, sync) enough to debug failures and design robust tests.
Programming: High proficiency in Python; experience with Rust for runtime integration is a significant plus.
Compliance: This position requires access to export-controlled information under ITAR. Only U.S. persons are permitted to access such information.
Background: Must be willing to submit to a background check.

Nice-to-Have

On-device inference optimization (TensorRT, ONNX, quantization)
Weak/self-supervised learning and domain adaptation
Fusion/tracking experience (temporal models, confidence calibration)
Passion for building robots as a hobby

About the interview

Application screen phone call (30 min)
Virtual interview with co-founder #1 (30 min via MS Teams)
Paid take-home ($500, ~4-8 hours)
Review work
Virtual interview with co-founder #2 (45 min via MS Teams)
In-person visit to Austin/Offer

Similar jobs

Work in company