Mid-Senior Software Engineer – Computer Vision
Pubblicato il 15-10-2026 - Altro in Carate Brianza
We are looking for a Software Engineer with experience in integrating Computer Vision solutions to join our Vision team. The successful candidate will primarily be responsible for developing and integrating software applications that bring computer vision models into production across our robotics platform, both on edge devices and in the cloud.
The role will focus on designing robust and modular software pipelines for data acquisition, inference, inter-service communication, and AI model deployment, while collaborating closely with the AI, Software, and Hardware teams.
The selected candidate will work on:
Integrating computer vision models (object detection, segmentation, and pose estimation) into production software applications.
Developing software services and pipelines for image acquisition, inference, and post-processing.
Deploying AI applications on edge devices (NVIDIA Jetson) and cloud infrastructures.
Integrating with middleware, REST/gRPC APIs, messaging systems, and streaming protocols.
Optimizing application performance and managing the AI model lifecycle (ONNX, TensorRT).
Developing modular software in Python.
Containerizing applications with Docker and contributing to CI/CD pipelines.
Collaborating with AI, Software, and Hardware teams to deliver end-to-end integrated solutions.
Requirements
Bachelor's or Master's degree in Computer Science, Software Engineering, Robotics, or a related field.
At least 2 years of experience in software development with a focus on computer vision, robotic perception, or 3D vision systems.
Strong knowledge of Object-Oriented Programming in Python , including multithreading and asynchronous programming.
Experience with streaming protocols (e.g., WebRTC ) and IoT communication protocols (e.g., MQTT ).
Hands-on experience with RGB-D pipelines, point cloud processing, and 3D libraries (e.g., PCL ).
Experience developing or integrating deep learning models for object detection, segmentation, and pose estimation using PyTorch or TensorFlow .
Experience deploying and optimizing AI models on GPUs and edge devices using technologies such as ONNX Runtime, TensorRT, CUDA, and NVIDIA Jetson .
Experience with model conversion, FP16/INT8 quantization , and real-time inference optimization.
Familiarity with collaborative development workflows based on Git .
Nice to Have
Experience with ROS or ROS 2 .
Experience with Docker and MLOps infrastructures.
Experience building or maintaining CI/CD pipelines for machine learning models.
Familiarity with Vision-Language Models (VLMs) or other emerging AI models for robotics.
#J-18808-Ljbffr