Listing translated from German by Talent Club.
About the role:
Background and scientific classification
In the pharmaceutical environment, complete, consistent and auditable documents (e.g. URS, manufacturer documentation, software change reports) are crucial for quality, compliance and the correct implementation of requirements.
What you will achieve:
Objective of the Master's thesis
The aim of this Master's thesis is the development and systematic evaluation of an AI-supported approach to support the document review process in the field of Automation Engineering. In particular, it will be investigated to what extent selected AI use cases, compared to manual reviews, can improve the efficiency and quality of identifying inconsistencies in technical documents. In addition, suitable AI methods (e.g. rule-based approaches vs. NLP/LLM) will be analyzed as well as requirements for the design, governance and use of a compliantly deployable AI system.
Possible research questions
How effective are specific AI use cases (e.g. requirement coverage, consistency checking or delta analysis) compared to manual reviews in detecting inconsistencies in technical documents?
To what extent does AI measurably improve the document review process in terms of efficiency and quality?
What impact does the use of AI have on turnaround time and resource expenditure in the document review process in a regulated environment?
Which AI approaches (e.g. rule-based vs. NLP/LLM) are best suited for automated review of requirement specifications with regard to completeness and consistency?
How must an AI-supported system be designed (technology, governance, processes) to efficiently and compliantly support document review in Automation Engineering?
How must an AI-supported system be used and how must prompting be carried out to obtain repeatable, accurate results, and where are the limits in practical application?
Where are the methodological, technical and procedural limits of using AI in the document review of technical requirement specifications?
In which cases does the use of AI, compared to manual reviews, reach its limits with regard to accuracy, traceability and reliability in detecting inconsistencies?
Expected results
A structured and robust as-is analysis of the current document creation and review process in the field of Automation Engineering.
Creation of a use case catalog with prioritization and selection of pilot use cases.
Implementation in the form of a proof of concept of the use cases using different technologies.
Systematic comparison and technological classification of suitable AI approaches.
Quantitative evaluation of the AI approach and comparison with the previous process with regard to, among other things, efficiency, quality, process performance.
Determination and analysis of the systematic limits of using AI in the document creation and review process.
Creation of a guideline for the repeatable application of the AI solution.
What you bring:
Master's degree in automation engineering, computer science, data science, process engineering, industrial engineering or a comparable field
Knowledge in the area of AI applications, natural language processing, information retrieval, document management or digital quality assurance in text processing / image processing
Structured work in an environment with high requirements for quality, reliability, auditability and confidentiality
Analytical thinking as well as an independent and careful way of working
Good German and English skills in spoken and written form
Advantageous
Experience with structured document formats (e.g. templates, traceability tables, tables/metadata) and ideally with tools for document checking or versioning
Enjoyment of interdisciplinary collaboration and of transferring theoretical concepts into practice
What we offer:
For this important and responsible position, the salary is EUR 2,010.75 gross/month (full-time, chemical industry collective agreement).
Awards as a top employer and certified family-friendly company
Comprehensive further education and training offers as well as personal development and mentoring program
Diverse development programs (talent, trainee, apprentice program)
Employee referral and recognition programs, employee stock purchase plan
Active participation in various network groups (e.g. Diversity, Equity & Inclusion; Sustainability)
Diverse health offers (e.g. free vaccinations, psychological counseling, massages)
Fitness offers
Company events & celebrations
Company restaurant with subsidized prices
Company childcare / bilingual company kindergarten
Good public transport connections