Routing and Scheduling Optimisation (RSO) KTP Associate

ABL 1 Touch (ABL), a leading UK-wide automotive repair group, is partnering with the University of Portsmouth on a high-impact Knowledge Transfer Partnership (KTP) to transform vehicle repair operations through artificial intelligence.

This is a great opportunity for an Embedded Operational Research (OR)/Logistic/ML scientist who is keen to expand their wider commercial and project management experience as an additional training and development budget of £2,000 pa is also provided.

The ideal candidate will have a solid foundation in OR/AI and software development, is enthusiastic about working on innovative technology within a supportive commercial environment, while also developing leadership and project management skills.

The post will provide the individual with an opportunity to make a significant contribution to the company’s innovation policy.

The successful applicant will be highly motivated and able to demonstrate some previous experience in a relevant role.

This appointment is a fixed-term contract (30 months). Hybrid working is possible for this position between ABL sites in Portsmouth or Southampton, with a need to attend the Reigate office or other locations that allow you to spend time with the relevant operational teams. You will also be able to work from home where the need to be with an ABL team member is limited.

This major project will recruit two Associates: one focused on machine learning and computer vision, and the other on operational optimisation. This advert is for the Routing and Scheduling Optimisation (RSO) KTP Associate, who will play a pivotal role in designing, training, and deploying intelligent systems for automated damage assessment.

The RSO Associate will work at the intersection of combinatorial optimisation, dynamic scheduling, and industrial operations, applying advanced mathematical and algorithmic techniques to real-world challenges in the automotive repair sector. They will collaborate closely with ABL’s technical team and academic supervisors to design and implement a robust optimisation framework for allocating vehicle repair jobs to the most suitable sites, under complex and evolving operational constraints.

The role will involve developing and refining advanced optimisation models—ranging from mixed integer programming for small-scale problems to heuristics, metaheuristics, and AI-driven approaches for large-scale, real-time scenarios. Core objectives include minimising repair completion time and cost while maximising customer satisfaction, taking into account site capacities, technical capabilities, transportation times and costs, procurement lead times for automotive parts, and opportunities for consolidation to improve operational efficiency.