Sr. ML Engineer, Perception

About the role

Who We Are:

Aurelius Systems is a VC backed defense tech startup building autonomous, edge deployed directed energy systems for counter-UAS. We build laser weapons to shoot down drones.

We're a small team of engineers, former US military operators, and subject matter experts scaling America's directed energy dominance. The first cost effective, reliable and robust laser weapon system.

Our namesake isn't an accident. Marcus Aurelius wrote about doing the work in front of you, every day, without excuses. Henry Ford didn't wait for permission to reinvent manufacturing. That's how we operate — small team, unreasonable output, no hiding behind the unachievable.

In addition to our San Francisco lab, we’ve opened a Detroit manufacturing hub and we field test weekly on our own 400-acre private range.

The Role and Your Impact:

We need a Senior Machine Learning Engineer to lead the perception stack for Archimedes — detection, tracking, classification, and sensor fusion across the targeting chain. You're the seasoned engineer who's shipped perception in something that had to work outside a benchmark. You'll partner directly with our CTO and the robotics software team, and own perception as a domain.

What You'll Own:

- Perception architecture across detection, tracking, classification, and sensor fusion

- ML model development, training pipelines, and on-device deployment

- Multi-sensor fusion across EO/IR and other sensors as relevant to the targeting chain

- Real-time performance optimization on embedded targets

- Mentorship of perception engineers as the team grows

- Direct partnership with controls, robotics SWE, and hardware on what's actually achievable

What We're Looking For:

- 5+ years building and shipping perception systems on real hardware

- Strong Python and C++ with deep ML engineering experience

- Computer vision, tracking, and detection in real-time, real-world conditions

- On-device deployment experience using TensorRT, ONNX, or equivalent

- Track record optimizing perception for embedded compute and latency budgets

Where you probably come from: Perception roles at defense companies, autonomy, perception-heavy robotics, or aerospace programs that put perception in front of real targets.

We want to talk if: You've shipped a perception system that ran on real hardware against real targets. You know the gap between paper SOTA and what survives field conditions.

Not a fit if: Your background is research only without deployment, you're a new grad (we'll have a junior role later), or your CV experience is offline batch processing only.

Nice to Haves:

- Counter-UAS or aerial target tracking experience

- Radar or RF perception

- Classified program experience

- Sensor fusion in adversarial or denied environments