Pre-doctoral researcher

AI for Automated Visual Inspection in Low-resource Domains

Ref. 2022_020

Job Description

The IBM Zurich Research Laboratory is leading the design of AI based innovative solutions for enterprise visual inspection. The technology created in our team is powering IBM mainstream products, such as Maximo Visual Inspection and has been successfully applied to the 3rd longest suspension bridge in the world - the Storebaelt.

We are looking to strengthen our team with a skilled and highly motivated PhD researcher, who will research and contribute to design solutions in the domain of automatic visual inspection of civil assets. The successful candidate will join our team at the IBM Zurich Research Laboratory, having the opportunity to work in a unique research-corporate environment. As part of our team, the student will collaborate with experienced Research Scientists and AI Software Engineers to research, prototype, and implement innovative solutions which will eventually be powering large-scale AI services on Cloud.

The candidate shall be highly motivated and versatile, as there will be many challenges to tackle in order to push forward the state-of-the-art in visual inspection. Example of research topics that will be subject of this PhD are:

  • Adaptivity of instance segmentation models to different domains (e.g., different backgrounds, objects to detect, defect types) and environments (e.g., changing weather, time in the day).
  • Tackling the low-resource problem by data augmentation and data synthesis.
  • Enhance the performance of specialized defects detection models by designing multi-stage pipelines which include domain knowledge.
  • Active learning and AI-based annotation helpers, to keep the human in the loop of the AI model lifecycle.

Core activities

  • Research new methodologies for advancing the state-of-the-art of computer-assisted visual inspection in real-life low-resource domain scenarios.
  • Publish these to top AI conferences and design end-to-end demos to showcase the work.
  • Develop data science and machine learning solutions at scale on distributed systems.
  • Implement AI workflows, with attention to the full model lifecycle.
  • Design and implement prototypes to be included in our internal platform for Visual Inspection.

Minimum qualifications

  • Outstanding university track record, with background in Computing, Machine Learning, Mathematics, Statistics, or equivalent fields.
  • Proven programming experience in Python (or equivalent experience in C++).
  • Proficiency in UNIX/Linux.
  • Ability to speak and write in English fluently.
  • Self-motivation with passion for technology and innovation.

Nice to have

  • Experience with machine learning, deep learning, and/or computer vision.
  • Contributions to open-source projects.
  • Proven record of participation in Kaggle competitions (or similar).
  • Publications in top AI conferences (e.g., NeurIPS, AAAI, etc.).
  • Experience with DevOPs or public cloud environments.

Diversity

IBM is committed to diversity at the workplace. With us you will find an open, multicultural environment. Excellent flexible working arrangements enable all genders to strike the desired balance between their professional development and their personal lives.

How to apply

If you are interested in this exciting position, please submit your most recent curriculum vitae. We encourage candidates to also share a 3-minute video, in which they introduce themselves, as well as highlight their motivation (the video is not mandatory).