Sr. ML Engineer, Perception

Aurelius Systems•San Francisco, CA
•$190,000 - $222,000•Onsite

About The Position

Aurelius is an autonomous directed energy company developing American-made laser-based counter-UAS systems. Its Archimedes autonomous laser turret uses a high-power laser, radar, and machine vision to detect, track, and defeat small drones. The company designs in San Francisco, manufactures in Detroit, and tests onsite at its own counter-UAS range. The Sr. ML Engineer, Perception will own perception for Archimedes, turning live EO/IR and other sensor data into reliable detection and tracking on a moving, edge-deployed system. The role covers the full machine learning pipeline, including data decisions, model training and evaluation, embedded deployment, and using range results to guide improvements. Initial work focuses on increasing the resilience of the existing perception pipeline, with field data from deployed systems providing further opportunities to improve performance. The engineer will collaborate directly with robotics software, controls, and hardware engineers and help mentor perception engineers as the team grows. The role is onsite five days a week in San Francisco. Core operating hours are Monday through Friday, 9 a.m. to 6 p.m. Pacific Time; additional late nights or weekends may be required during sprints, ramp-up periods, conferences, deployments, or events. U.S. citizenship is required for export-controlled work.

Requirements

  • Personally trained, evaluated, and deployed detection, tracking, or segmentation models on a physical system or live sensor stream.
  • Hands-on experience with multi-object tracking and state estimation on real sensor data, including Kalman filters, IMM, data association, and track management.
  • Experience across the robotics ML pipeline: data, training, evaluation, deployment, and improvement based on real-world results.
  • Strong Python skills and ability to read and write C++, including understanding the path from a 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.

Nice To Haves

  • EO/IR perception, radar-camera fusion, or experience with small aerial targets.
  • Hands-on experience with current detector families such as YOLO and RT-DETR.
  • Data strategies for physical systems, including sim-to-real or fine-tuning on field data.
  • JAX or PyTorch experience with robotics models.
  • On-device inference optimization against a measured latency budget.
  • Distinctive, self-directed projects that solved a specific technical gap.

Responsibilities

  • Own perception for Archimedes, converting live EO/IR and other sensor data into reliable detection and tracking on a moving, edge-deployed system.
  • Make data decisions, train and evaluate models, deploy them on embedded compute, and use range results to guide improvements.
  • Improve the resilience of the existing perception pipeline and use field data to improve performance as more systems are deployed.
  • Define and document the perception architecture across detection, tracking, classification, and EO/IR fusion in agreement with controls and robotics software teams.
  • Build a repeatable process for turning range captures, hard negatives, and field failures into training and evaluation improvements.
  • Establish and improve on-device latency and performance baselines.
  • Diagnose and address field failure modes, including tiny targets, clutter, ego-motion, and track handoff to controls.
  • Work with hardware and controls engineers on range days to validate system changes.
  • Help mentor perception engineers as the team grows.

Benefits

  • A comprehensive, competitive benefits package available at little to no cost to employees, supporting health, recovery, and future needs.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service