Job
- Level
- Junior
- Job Field
- Software
- Employment Type
- Full Time
- Contract Type
- Internship / school internship
- Location
- Böblingen
- Working Model
- Hybrid, Onsite
Job Summary
In this role, you will work on inferring implicit user feedback in dialogue systems, developing models to predict dissatisfaction, and implementing evaluation pipelines in machine learning.
Job Technologies
Your role in the team
- In our cross-functional team "Holistic Customer Centered Experiences," we are designing the guiding principles of our UX vision for the future Mercedes-Benz User Experience.
- With this vision, we are developing a new, holistic customer experience in our vehicles and beyond.
- Modern task-oriented dialogue agents rely heavily on explicit user feedback or task completion metrics to evaluate the success of an interaction.
- In real-world environments, such as in-vehicle assistants in the automotive sector, explicit feedback is, however, extremely rare.
- This work addresses the inference of implicit, multimodal feedback as a central problem in machine learning.
- The focus is on the algorithmic tracking of the latent user state (Belief State) under partial observability.
- By predicting dissatisfaction early in the temporal interaction flow, the model enables a closed AI system to proactively adjust its dialogue policy before the interaction fails.
- The primary scientific contribution will be the training of the model and the development of a pipeline for its evaluation from a machine learning perspective.
- Development of latent models: construction and training of recurrent belief-state models over the course of interaction, as well as benchmarking against purely text-based LLMs and multimodal late-fusion classifiers.
- Design rigorous ML evaluations: Implementation of evaluation pipelines with a strong focus on early inference.
- Isolation of causal signals: Training of negative control variables (e.g., current road context or baseline mood) to mathematically demonstrate that the model indeed isolates the causal influence of the assistant on user satisfaction and does not merely capture environmental noise.
- The final topic selection is made in consultation with the university, you, and us.
This text has been machine translated. Show original
Our expectations of you
Qualifications
- Enrolled in a degree program: (Media) Computer Science, Artificial Intelligence, Machine Learning, Data Science, Engineering Psychology, or a comparable program with a relevant focus.
- In-depth knowledge of Artificial Intelligence and Machine Learning.
- Strong interest in technological trends and their potentials.
- Enjoyment of independent work and challenges, evident through high motivation, willingness to implement, commitment, team spirit, active communication, and an analytical and strategic approach to work.
- Proficient in spoken and written German and English.
- Proficient in MS Office and software development tools such as Atlassian Confluence, Jira, etc.
- Ideally, a Class B driver's license.
Experience
- Initial experience in analyzing multimodal datasets.
This text has been machine translated. Show original
What we offer
- The activity can commence from August 2026.
This text has been machine translated. Show original
Benefits
More net
- 🏝️Summer and Christmas Bonus
- 🍰Employee Stock Option
- 💻Company Notebook for Private Use
- 🚙Company Car
- 📱Company Phone for Private Use
- 🛍Employee Discount
- 👴🏻Company Retirement Provision
- 👷♂️Additional Insurance
Health, Fitness & Fun
Work-Life-Integration
- 🐕Animals Welcome
- 🏠Home Office
- 🍼Day Care for Kids
- 🅿️Employee Parking Space
- 🚌Excellent Traffic Connections
- ⏰Flexible Working Hours
Food & Drink
Topics that you deal with on the job
Job Locations
This is your employer
Mercedes - Benz AG
The Mercedes-Benz brand of automobiles is a registered trademark of Daimler AG. In 2016, sales of new vehicles reached 2.08 million. With business units including Mercedes-Benz Cars, Daimler Trucks, Mercedes-Benz Vans, Daimler Buses and Daimler Mobility, the company ranks among the leading providers of premium cars and is the world's largest commercial vehicle manufacturer.
Description
- Founding year
- 1926
- Company Type
- Established Company
- Working Model
- Hybrid, Onsite
- Industry
- Vehicle Manufacturing, Supplier, Industry, Production
Dev Reviews
by devworkplaces.com
Total
(1 Review)4.4
Workingconditions
4.8Engineering
4.0Career Growth
4.8Culture
4.2
Student thesis: Multimodal inference of user satisfaction in dialogue systems
- Location
- Böblingen
- Working Model
- Hybrid, Onsite
- Diversity
- Open for all genders
