Computer Vision Engineer
Job Description
Job Position: Computer Vision Engineer
Experience: 2–5 years
Job Location: Onsite / Remote (India or Germany)
Employment Type: Full-time
Position Summary
As a Computer Vision Engineer, you will design, build, and optimize systems that leverage advanced vision algorithms to solve complex real-world challenges. You will work on tasks such as image segmentation, feature detection, motion detection, object tracking, and scene understanding. This role requires hands-on experience with production deployments, real-time processing, and integration of vision with multimodal data sources for robust, scalable AI pipelines.
Roles and Responsibilities
- Design and implement advanced computer vision algorithms including segmentation, detection, tracking, and motion analysis.
- Build real-time vision systems for robotics, drones, and remote sensing applications.
- Develop and optimize deep learning models (CNNs, Vision Transformers, DeTR, YOLO, Mask R-CNN, etc.).
- Implement pre-processing, augmentation, and domain adaptation techniques for robust model performance.
- Deploy and maintain production-grade computer vision models with MLOps best practices.
- Collaborate with hardware and robotics teams to integrate CV pipelines with edge devices and sensors.
- Benchmark, test, and refine models for latency, throughput, and accuracy trade-offs.
- Ensure system reliability, scalability, and security in real-world deployments.
- Build multi-modal AI systems combining vision with text, RS data, and structured/unstructured datasets.
- Document solutions and contribute to internal research and innovation.
Skills
- Strong proficiency in Python with experience in OpenCV, PyTorch, TensorFlow, and ONNX.
- Solid understanding of image segmentation, feature detection, optical flow, and motion estimation.
- Experience with real-time computer vision systems and deployment on edge devices (NVIDIA Jetson, TPU, FPGA).
- Expertise in training and fine-tuning deep learning vision models.
- Hands-on experience with MLOps tools for deployment, monitoring, and scaling (MLflow, Kubeflow, Airflow, Docker, Kubernetes).
- Familiarity with camera systems, calibration, and 3D vision techniques (stereo, SLAM, depth estimation).
- Experience working with large-scale image/video datasets and efficient annotation pipelines.
- Strong experience in multi-modal systems development (vision + LLM, vision + RS data, fusion with tabular/graph data).
- Understanding of cloud-native deployments (AWS/GCP/Azure).
Qualifications
- Bachelor’s or master’s degree in computer science, AI/ML, Robotics, or related field.
- Demonstrated track record of building production-grade computer vision and multimodal systems.
- Strong mathematical background in linear algebra, optimization, and probability as applied to vision tasks.
About KIREAP
KIREAP headquartered in Switzerland, is a rapidly growing global / international deep tech start-up tackling major sustainability challenges starting first with the agriculture value chain, moving to Remote Sensing, Logistic Drones, Space and beyond in different phases of the company. We are currently valued at close $200Mn expected to reach unicorn status within a year before launching its IPO. Why we started with Agriculture – we need to bring high end space and aerial and other technologies at no cost to the farmers which represent 1/5th of humanity. We need to secure a sustainable and affordable food system for a growing population within our planetary boundaries. Our solutions include deep-tech technologies both in hardware and software like Gen AI (artificial intelligence, Quantum Computing and Blockchain-enabled digital platform to drones and aerial mobility).
