
Sr. ML Engineer, Perception
Aurelius Systems8 hours ago
Base Salary
$190k - $222k/yr
Responsibilities
- Own perception for an edge-deployed autonomous laser turret using live EO/IR and other sensor data.
- Define architecture across detection, tracking, classification, and EO/IR fusion with controls and robotics software teams.
- Build pipelines that convert range captures, hard negatives, and field failures into training and evaluation improvements.
- Establish and improve on-device latency and performance baselines.
- Diagnose field failure modes including tiny targets, clutter, ego-motion, and track handoff to controls.
- Train, evaluate, deploy, and improve models based on real-world range results.
- Collaborate with robotics software, controls, and hardware engineers during onsite range testing.
- Mentor perception engineers as the team grows.
Requirements
- Personally trained, evaluated, and deployed detection, tracking, or segmentation models on a physical system or live sensor stream.
- Experience across the robotics ML pipeline, including data, training, evaluation, deployment, and improvement from real-world results.
- Strong Python and working C++ skills, including the path from trained model to on-device inference.
- Experience measuring and improving performance under real-time latency and compute constraints.
- U.S. citizenship required for export-controlled work.
- Preferred experience with EO/IR perception, radar-camera fusion, small aerial targets, or track management.
- Preferred experience with data strategies for physical systems, sim-to-real, field-data fine-tuning, JAX, PyTorch, robotics models, or on-device inference optimization.
- Distinctive, self-directed projects that solved a specific technical gap are valued.
Benefits
- Comprehensive competitive benefits package available at little to no cost to employees, supporting health and recovery.
- Onsite five days per week in San Francisco, Monday through Friday, 9am to 6pm Pacific Time.
- The role may require late nights and weekends during sprints and ramp-up periods, as well as work during conferences, deployments, and events.
Categories
ML EngineeringRobotics
About Aurelius Systems
Aurelius Systems builds AI-enabled directed-energy laser systems to defeat unmanned aerial systems (cUAS) for defense and critical infrastructure operators. The company designs, manufactures, and deploys autonomous, edge-deployed counter-drone platforms, including the Archimedes system, and supports field testing and integration with end users. Privately held and venture-backed, Aurelius is headquartered in San Francisco and emphasizes rapid transition from R&D to operational field deployments with military and security operators.