Autonomous Drone Vision Engineer

GrazeMate, Inc.; Sydney; On-site; AUD 120,000 - 190,000; Full time

Benefits offered by this job

Early stage equity

Competitive salary

Job summary

Brumby, based in Sydney, is hiring a Perception Engineer to own how our drones see the world and act on it. You will develop onboard perception to find, count, and track cattle from the air, with edge inference on Jetson and real-time, offline testing using SITL/Gazebo.

You’ll fuse camera, thermal, and GNSS/IMU data to geo-locate every animal and inform autonomous flight decisions. The role is hands-on, with ownership and close collaboration with the founder and engineering team.

Qualifications

• Must have trained perception models deployed on Jetson using TensorRT INT8 to meet latency budgets.
• Built DeepStream or GStreamer pipelines that run in production.
• Strong sensor fusion across camera and GNSS/IMU, including pose estimation and geo-registration.
• ROS 2 in production on real hardware, including Jazzy, DDS tuning, and MAVROS.
• Trained models like YOLO in data with limited compute and real-world messy footage.
• Experience with SITL, Gazebo, and rosbag for testing before flight.
• Degree in CS/Robotics/Mechatronics or EE, or research in perception/autonomy.

Responsibilities

• Onboard perception to detect, count, and track cattle from the air day and night.
• Edge inference pipelines on Jetson with real-time performance and no connectivity.
• Fuse camera, thermal, and GNSS/IMU data to geolocate every animal in the paddock.
• Bridge perception and autonomy to guide how the drone flies.
• Use simulation and replay tooling to validate the full loop before field use.

Skills

Jetson perception

DeepStream pipelines

Sensor fusion GNSS/IMU

ROS 2 in production

YOLO in limited compute

Education

CS/Robotics/Mechatronics or EE degree

Tools

Jetson

TensorRT/INT8

DeepStream

ROS 2 (Jazzy, MAVROS)

Job description

Brumby, based in Sydney, is hiring a Perception Engineer to own how our drones see the world and act on it. You will develop onboard perception to find, count, and track cattle from the air, with edge inference on Jetson and real-time, offline testing using SITL/Gazebo.

You’ll fuse camera, thermal, and GNSS/IMU data to geo-locate every animal and inform autonomous flight decisions. The role is hands-on, with ownership and close collaboration with the founder and engineering team.