Senior ML / Perception Engineer (Embedded Vision)

At

TreeX Robotics

, we are

redefining the Drone

. We are moving beyond contactless flight to interactive, autonomous flying robots that perform real physical work.

Our first mission: Bringing our drones to handle the delicate, physical labor that wine grapes demand

. As we scale, we are looking for a

core team member

for our AI development team.

This role is focused on building perception systems that

actually work in the field

, under real-world constraints.

What You’ll Do

• Own the full perception pipeline:

data → training → evaluation → deployment

• Develop and improve detection and segmentation models using RGB \+ depth data
• Build and maintain a

data engine

:

• Define labeling strategies and guidelines
• Drive dataset quality and consistency
• Handle noisy and imperfect data
• Ensure models generalize to

real-world conditions

:

• Changing lighting
• Occlusions
• Small / hard-to-detect objects
• Deploy models to

Jetson NX-based systems

• Ensure compatibility with TensorRT
• Perform basic export, validation, and debugging
• Collaborate closely with

software, robotics, and algorithm engineers

to integrate perception into the system

What We’re Looking For

• Strong experience building and deploying

computer vision models (detection \+ segmentation)

• Hands-on experience with

training pipelines and dataset iteration

• Proven ability to improve performance with

imperfect / noisy data

• Experience working with

real-world vision problems

(not only curated datasets)

• Practical understanding of

deployment constraints

(latency, memory, model size)

• Experience exporting models to

ONNX / TensorRT (or similar)

Nice to Have

• Experience with

RGB \+ depth / 3D perception

• Background in

robotics or embedded systems

• Familiarity with

edge devices (Jetson family)

What Success Looks Like

• A

reliable perception model

running on embedded hardware in real conditions

• A

data pipeline

that continuously improves model performance over time

Why This Role

• Work on

real-world problems

, not benchmark datasets

• Own a

critical part of the system end-to-end

• High autonomy and direct impact on product performance