Robotics Software Engineer – Machine Learning, Computer Vision & VLM

Location: Warsaw, Poland; onsite or hybrid

Company

hirify.global develops autonomous mobile robots and complete robotics solutions for industrial facilities, warehouses, and logistics centres, including robot software, autonomous navigation, sensor integration, and fleet management.

What you will do

• Develop machine-learning and computer-vision algorithms for autonomous robots, including detection, classification, segmentation, tracking, and semantic scene understanding.
• Process RGB, RGB-D, stereo, thermal, LiDAR, and other sensor data for recognising people, vehicles, forklifts, obstacles, and operational events.
• Prepare and version datasets, design training and validation workflows, select model architectures, and define model-quality metrics.
• Optimise, convert, and deploy models for real-time operation on onboard edge-computing platforms.
• Build monitoring and automated analysis tools to detect model degradation, unusual cases, false detections, and missed objects across the robot fleet.
• Develop perception components in ROS and ROS 2, integrate outputs with navigation, safety, and mission-execution systems, and test algorithms in simulation and on physical robots.

Requirements

• At least 2 years of relevant professional experience in machine learning, deep learning, or computer vision.
• Very good knowledge of Python and practical knowledge of OpenCV.
• Knowledge of at least one framework: PyTorch, TensorFlow, or JAX.
• Experience with object detection, classification, segmentation, or tracking; dataset preparation and validation; model-quality metrics; generalisation, overfitting, and data augmentation.
• Experience deploying models to production, analysing model errors and edge cases, and working with data from real sensors.
• Knowledge of Linux and Git, plus English sufficient for confident work with technical documentation and research papers.

Nice to have

• Knowledge of C++, ROS or ROS 2, NVIDIA Jetson, CUDA, TensorRT, DeepStream, ONNX, or model-optimisation tools.
• Experience with YOLO, Detectron2, MMDetection, Vision Transformers, multimodal models, or VLM prompt design, fine-tuning, and evaluation.
• Experience with RGB-D, stereo, or thermal cameras, sensor fusion, point clouds, MLOps, data and model versioning, or experiment tracking.
• Experience with Docker, CI/CD, automated model testing, synthetic data, simulation, active learning, continual learning, or domain adaptation.
• Experience in mobile robotics, automotive, or safety systems, or a relevant publication, open-source project, or computer-vision portfolio.

Culture & Benefits

• Influence the perception system of autonomous robots using real data collected at customer sites.
• Work with cameras, LiDARs, physical robots, edge platforms, and a dedicated testing environment.
• Build a complete model-development process from data preparation through fleet deployment.
• Combine robotics, computer vision, machine learning, and cloud systems.
• Work with a high degree of independence and direct cooperation with the technical team.
• Full-time employment with compensation aligned to experience and responsibility.