Senior Computer Vision Engineer

Location: Singapore, Singapore, Singapore

Department: RDO

Workplace: on_site

Employment Type: full

Description

Rapsodo is a global Sports Technology company with offices in the USA, Singapore, Turkey, and Japan. We develop cutting-edge sports analytics products that are data-driven, portable, and easy to use, empowering athletes at all levels to analyze and improve their performance. From Major League Baseball pitchers to professional Golf tour players, athletes around the world rely on Rapsodo technology to refine their game.

Job Description

Our algorithm team designs and implements state-of-the-art computer vision and deep learning solutions for Rapsodo’s advanced sports analytics products. As a Senior Computer Vision Engineer, you will develop cutting-edge 3D vision, image processing, and AI-driven measurement solutions that help athletes reach their full potential.

This role requires a strong foundation in computer vision, deep learning, and embedded AI, with opportunities to contribute to both new product development and optimization of existing models for edge computing.

Key Responsibilities

• Develop Advanced Vision Algorithms – Design, implement, and optimize 3D vision, image classification, segmentation, and feature extraction algorithms.
• Neural Network Development – Architect and train CNNs and custom deep learning models using PyTorch, TensorFlow, or ONNX for real-time applications.
• Embedded AI & Edge Optimization – Optimize and port vision models to embedded platforms (ARM, GPU, TPU, or custom accelerators) for high-performance, low-latency inference.
• Camera Calibration & 3D Vision – Develop and enhance multi-camera calibration, stereo vision, and 3D reconstruction techniques.
• Software Architecture & API Design – Design scalable computer vision pipelines and APIs for seamless integration with Rapsodo’s product ecosystem.
• Performance Optimization – Apply quantization, pruning, and model compression techniques to enhance real-time inference efficiency on resource-constrained

Requirements

• Education – Master’s or Ph.D. in Computer Science, AI, Robotics, or a related field, specializing in Computer Vision & Image Processing.
• Experience – 6-8+ years of hands-on experience in computer vision, deep learning, and real-time image processing.

Technical Expertise:

• 3D Vision & Camera Calibration – Strong foundation in multi-camera setups, stereo vision, and geometric transformations.
• Deep Learning & Vision Models – Expertise in CNNs, object detection, pose estimation, segmentation, and feature extraction.
• AI Frameworks & Optimization – Hands-on experience with PyTorch, TensorFlow, OpenCV, and model compression techniques (quantization, pruning, distillation, etc.).
• Embedded Deployment – Experience optimizing and deploying deep learning models on ARM, GPU, TPU, or custom edge AI hardware.
• Programming & Software Development – Strong proficiency in C/C++ with some Python, and experience in software architecture and API design.
• Problem-Solving & Communication – Strong analytical skills and ability to collaborate across teams, explaining technical concepts to diverse stakeholders.

Why Join Us?

• At Rapsodo, you will work on high-impact, real-time AI-driven vision systems that push the boundaries of sports analytics. Join a fast-growing, innovation-driven team to shape the future of sports technology.
• Apply now and be part of our cutting-edge vision engineering team!