Computer Vision & Embedded Systems Engineer
Role details
Job location
Tech stack
Job description
Join our team developing the hottest apps in the industrial mushroom farming sector. As Senior Computer Vision & Embedded Systems Engineer focused on leading-edge computer vision & robotics applications, you will play a pivotal role in developing and applying cutting-edge technologies to optimize key aspects of our mushroom cultivation processes.
At MycoSense, we aren't just building models; we are building the eyes of industrial mushroom cultivation. You will be responsible for the end-to-end vision pipeline that powers our vision units and robot integrations. We work in the real world-where lighting changes, dust exists, and latency kills., * Architect Vision Pipelines: Design and deploy real-time CV systems for mushroom detection, grading, and room scanning that run 24/7 in industrial environments.
-
Hardware Ownership: Select and integrate industrial camera sensors, optimize optics, and manage the vision interface with NVIDIA Jetson Orin modules.
-
Edge Optimization: Take models from PyTorch/TensorFlow and squeeze every millisecond of performance out of them using TensorRT, CUDA, and C++.
-
Robotics Integration: Work directly with the robotics team to close the loop between vision perception and high-speed robotic picking (Delta-robots).
-
Physical Debugging: Solve the hard problems of "Vision in the Wild," including motion blur, varying focal planes, and environmental interference.
Requirements
Do you have experience in Python?, Do you have a Master's degree?, * Experience: 5+ years of professional experience in Computer Vision, specifically for industrial automation, robotics, or medical imaging.
-
The Stack: Advanced proficiency in C++ and Python. If you can't write a performant C++ wrapper for a vision task, this isn't the role for you.
-
The Hardware: Deep hands-on experience with the NVIDIA Jetson ecosystem (Orin/Xavier) and the DeepStream SDK.
-
Library Mastery: You know OpenCV inside and out (not just the high-level wrappers).
-
Deployment: Proven track record of deploying Deep Learning models into production environments where "latency" is a critical KPI.
-
Education: Master's or Ph.D. in CS, EE, or Robotics-but your portfolio of shipped physical products matters more than your thesis.