Jr. AI Engineer

Thingtrax is building an Agentic Manufacturing Operations platform to fundamentally change how factories run. By deploying AI-powered agents including computer vision systems directly on production lines, we enable manufacturing operations that can observe, reason, and act in real time. Partnering closely with manufacturers, especially in food and beverage, we're helping teams reduce waste, improve quality, and move from manual intervention to autonomous, continuously optimised operations.

Key Responsibilities

• Develop and optimize computer vision pipelines for object detection, classification, tracking, and OCR.
• Implement solutions using OpenCV, PyTorch / TensorFlow, and deep learning models.
• Assist in deploying models on edge devices such as Jetson, Raspberry Pi, or industrial PCs.
• Support integration with cloud-based services including inference APIs, storage, and logging.
• Collect, preprocess, and annotate image and video datasets.
• Perform model evaluation, benchmarking, and basic optimization.
• Collaborate with senior engineers on experimentation and applied research.
• Maintain documentation and version control using Git.
• Assist in installation, configuration, and support of AI and IoT solutions for clients.
• Collaborate with product and sales teams to support trials, site surveys, and ensure solutions meet customer needs.
• Configure and test hardware and software components for deployment.
• Troubleshoot technical issues and visit client sites as needed to resolve problems.
• Support development and debugging of AI and embedded systems code. Work in Agile teams following Scrum methodologies.
• Contribute to prototyping and MVP development for new AI technologies
  
  

Requirements

• Bachelor's degree in AI/CS/SE (mandatory).
• 1 to 2 years of hands-on experience in computer vision and AI model development and deployment.
• Strong programming skills in Python; knowledge of C#, C, or C++ is a plus.
• Hands-on experience with object detection models (YOLO, SSD, Faster R-CNN, etc.).
• Experience with OCR frameworks such as Tesseract, EasyOCR, or PaddleOCR.
• Basic understanding of tracking algorithms (Centroid, SORT, DeepSORT).
• Experience with OpenCV and image processing techniques.
• Solid understanding of Linux operating systems and command-line tools.
• Familiarity with networking protocols such as TCP/IP and Wi-Fi.
• Experience working in Agile environments and knowledge of TestDriven Development (TDD).
• Strong debugging and problem-solving skills.
• Customer-facing or consultancy experience is an advantage