KTP Associate in AI & Robotics for Recycling

The duties of the post will include:

• Designing and implementing AI and sensor-based solutions for automated waste recognition and sorting
• Developing and training deep learning models for waste recognition, classification, and segmentation using multimodal sensor data (RGB, NIR, depth)
• Designing, calibrating, and integrating multi-sensor acquisition systems for real-time industrial waste sorting environments
• Deploying and optimising AI models on edge-computing devices to achieve low-latency, high-throughput performance
• Integrating AI perception outputs with mechanical conveyor and actuation systems for automated sorting control
• Testing, validating, and refining the integrated AI-based waste sorting system under industrial operating conditions, ensuring robustness and scalability
• Supporting company scale up and exploitation of new technology
• Acting as project lead, to progress the project and ensure milestones are met to a timely manner
• Embedding technology, training and upskilling company staff
• Participating in academic and/or industrial conferences and other events, to disseminate and present research outcomes to the wider community

These duties are a guide to the work that the post holder will initially be required to undertake. They may be changed from time to time to meet changing circumstances.

Key Requirements

Qualifications

• BSc in Computer Science, Electronic Engineering, Robotics, or a related field
• MSc or equivalent industry experience in Artificial Intelligence, Computer Vision, or Embedded Systems

Skills & knowledge

• Strong understanding of machine learning and computer vision, including supervised/unsupervised learning methods
• Knowledge of image processing, feature extraction, and sensor calibration techniques
• Experience employing deep learning frameworks (e.g. PyTorch, TensorFlow)
• Experience implementing object detection/classification models (e.g. YOLO, Faster R-CNN)
• Proficiency in Python and C/C++, with experience of software engineering best practices (e.g., version control, testing)
• Experience developing real-time systems, edge computing solutions (e.g. NVIDIA Jetson), and sensor fusion algorithms
• Understanding of data acquisition and annotation processes, and practical experience with tools such as Label Studio or Roboflow
• Awareness of health and safety considerations when working with industrial equipment

Attributes

• Strong analytical and problem-solving skills
• Ability to work as part of a team and to work independently and manage own workload effectively
• Willingness to engage in hands-on testing in industrial environments
• Excellent communication and interpersonal skills, with the ability to collaborate across academic, industrial, and technical stakeholders and to explain technical concepts to non-technical colleagues
• Self-motivated, proactive, and able to take initiative in progressing project tasks
• Commitment to professional development and continuous learning
• Possessing a full, UK-valid driving licence and access to a personal vehicle (company premises not accessible by public transport)

Benefits

As a KTP Associate, the post will offer the following benefits:

• A personal development budget of £5,000 (exclusive of salary)
• Management training and mentoring by an Innovate UK KTP Adviser
• An interesting and challenging role, with exposure to a variety of stakeholders
• Full access to university resources to complete the project
• World-leading Academic and Company project supervision, with project support by a dedicated, sector leading KTP Office

IMPORTANT REQUIREMENT – A full, valid driving licence (permittable for use in the UK) and access to a personal vehicle are essential, as the company premises are not accessible by public transport.

This is an on-site based position, with some working from the University of Essex Colchester campus.

The University of Essex, in partnership with Firstgrade, offers an exciting opportunity to a graduate with the relevant skills and knowledge to revolutionise waste sorting in skips by developing an AI-powered system that automatically screens and sorts mixed construction waste with greater speed, accuracy, and efficiency.