SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Aurelius Systems is a VC-backed defense tech startup building autonomous, edge-deployed directed energy systems (laser weapons) for counter-UAS applications. The company operates from San Francisco with a manufacturing hub in Detroit and conducts weekly field tests on a 400-acre private range.
As a Perception Engineer, you will own the end-to-end perception and sensor-fusion stack for laser-based defense systems. Your responsibilities include designing, training, and deploying vision and sensor-based ML models (YOLO, RT-DETR, CNNs) for object detection, classification, and segmentation. You will integrate multi-modal sensor data (RGB, thermal, LiDAR/ToF, IMU, encoders) to produce robust, real-time Regions of Interest (ROIs) and develop high and low-level image-processing techniques such as deconvolution and motion-isolation for low-SNR detection.
You will collaborate closely with hardware teams to integrate and troubleshoot sensors over GigE Vision, USB3 Vision, CAN, SPI, and I²C protocols. This includes developing and debugging embedded firmware in C/C++ or Rust for microcontrollers (STM32, NXP, TI) and FPGAs using VHDL/Verilog within RTOS environments. You will build scalable data ingestion, labeling, augmentation, and storage pipelines handling 100k+ labeled frames, optimize inference frameworks for edge deployment (GPU/FPGA) achieving ≥500 Hz throughput, and develop dashboards for drift analysis and performance monitoring.
The ideal candidate has 2–6+ years in computer vision, sensor fusion, or robotics perception, with strong C++ and deep ML engineering experience. You should be hands-on with TensorFlow, PyTorch, TensorRT, and OpenVINO, with real-time detection and tracking experience in field conditions. ROS2, Docker, and CI/CD familiarity are expected. Critically, you must have shipped perception systems on real hardware against real targets—the company explicitly seeks engineers who understand the gap between research SOTA and field-deployed systems. Background in defense, autonomous vehicles, robotics, or aerospace is preferred. The role requires U.S. Person status due to export control regulations.
