Master Thesis in Continual Learning with Agentic Memories

Remote from: Germany
Annual salary: Undisclosed
Salary information is not provided for this position. Check our Salary Directory to estimate the average compensation for similar roles.
Department: Data Science & Analytics
Employment type: Full Time,
Job posted: 1 Jun 2026
Apply before: 1 Jul 2026
Experience level: Entry-Level
Junior
Views / Applies: 28 / 7

Invented for life.

Computer Software
1886

AI Summary

This master thesis position at Bosch focuses on continual learning and agentic memories, aiming to improve memory efficiency in large language model-based agents. The candidate will conduct literature review, adapt benchmarks, implement methods, and evaluate performance under tight deadlines. The role requires strong ML background, PyTorch skills, and research orientation. It offers a hybrid work model (70% remote) and lasts 6 months.

Role DNA

Job Complexity

Easy Hard

Pace & Pressure

Relaxed Fast-paced

Autonomy Level

Guided Full Ownership

Communication Load

Independent Highly Collaborative

AI Insight The role involves advanced ML concepts, independent research, and tight deadlines, requiring strong technical skills and self-motivation.

Salary Analysis

AI Insight The salary is not provided, but typical master thesis positions in Germany offer around €15-20 per hour, totaling about €30000 for 6 months full-time. This is below market rates for full-time ML roles but standard for academic theses.

Key Skills

Machine Learning Continual Learning Agentic Systems LLMs PyTorch Memory Management Research Deep Learning Python Git

Cover Letter Sample

I am writing to express my strong interest in the Master Thesis position on Continual Learning with Agentic Memories at Bosch. With a solid academic background in machine learning and hands-on experience with PyTorch, I am eager to contribute to advancing agent memory systems. My previous projects in deep learning and agentic systems have prepared me to tackle the challenges of this research. I am particularly drawn to Bosch's focus on practical applications and the opportunity to publish at top conferences. I am confident that my proactive and independent work style aligns well with the requirements of this role.

Possible Interview Questions

Can you explain the concept of catastrophic forgetting in continual learning and how it relates to agentic systems?

Catastrophic forgetting occurs when a model trained on new tasks loses performance on previously learned tasks. In agentic systems, agents must maintain knowledge over time while adapting to new information, making memory management crucial to avoid forgetting.

Describe a time you worked on a project with tight deadlines. How did you manage your time and ensure quality?

During my previous research project, I had to implement and evaluate a model within two weeks. I broke down tasks, prioritized experiments, and used version control to track progress. I communicated regularly with my advisor to adjust scope and ensure timely delivery.

How would you approach adapting an existing benchmark for Bosch-specific use cases?

I would first analyze the benchmark's structure and evaluate its relevance to Bosch's domain. Then, I would modify the data or task setup to reflect real-world scenarios, such as manufacturing or automotive contexts, while ensuring the benchmark remains challenging and measurable.

What methods do you know for improving memory efficiency in LLM-based agents?

Techniques include memory compression, selective forgetting, hierarchical memory structures, and using external memory stores. For token efficiency, methods like sparse attention, key-value caching, and summarization can reduce context size.

Why are you interested in this thesis topic, and what do you hope to achieve?

I am fascinated by how agents can learn continuously without forgetting. I hope to develop practical memory solutions that improve scalability and robustness, and contribute to the field through a publication at a major ML conference.

Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

Are you looking for an opportunity to explore how machine learning systems can continuously evolve while maintaining up to date knowledge? In this thesis, you will dive into the challenges of agentic systems, where growing context sizes drive up training costs, and focus on improving their working memory and token efficiency while applying common LLM models in continually learning and practice-oriented settings.

You will begin your thesis by conducting a comprehensive literature review on memory in agents, analyzing existing benchmark implementations, datasets, and methods to build a deep understanding of the field while also exploring the domain of continual learning.
Building on this foundation, you will adapt existing benchmarks or implement your own for Bosch-related use cases. In this context, you will write code to apply LLMs in an agentic setting, with a particular focus on agent memory.
Based on these insights, you will derive and implement methods aimed at improving the memory of continually learning agentic systems.
Finally, you will rigorously evaluate the performance of the developed approaches on standard academic benchmarks as well as Bosch use cases, while you will analyze scalability, robustness, and deployment potential.
You will carry out all of these tasks within a tight project timeline, with your results strongly encouraged to be submitted to major upcoming machine learning conferences, while performing effectively under deadline driven time pressure is mandatory.

Qualifications

Education: master studies in the field of Computer Science, Mathematics, Machine Learning or comparable with a focus on machine learning with very good grades
Experience and Knowledge:
- strong academic background in machine learning and (applied) mathematics
- solid programming skills in deep learning with PyTorch as well as proficiency in Git
- familiarity with job scheduling systems
- practical knowledge of agentic systems and their implementation in a research setting
- background in working with LLMs using PyTorch and Python
Personality and Working Practice: you are a motivated and research oriented person who takes a proactive and independent approach to problem solving and is able to work effectively under deadline pressure
Work Routine: our hybrid model provides you with a balanced mix of on site presence and remote work (70% remote, 30% in presence)
Enthusiasm: keen interest in independent problem solving
Languages: fluent in English and beginner in German

Additional Information

Start: according to prior agreement
Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations, list of previous code projects (need not be published) with brief descriptions and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need further information about the job?
Pascal Janetzky (Functional Department)
+49 173 4163104
Michael Klar (Functional Department)
+49 1525 8813540

Work #LikeABosch starts here: Apply now!

#LI-DNI

Apply now >