Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Project Machine Learning SystemsModule description #41341 / Version 1

← Module page Deutsche Fassung
Module / Version#41341 / #1
ValiditySince Winter semester 2026/27
Available language(s)English, German
Credit points12
Person responsible for the moduleBöhm, Matthias
GradingUngraded
Exam formatPortfolio examination
Language(s) of instructionEnglish

Affiliation

FacultyFakultät IV
InstituteInstitut für Softwaretechnik und Theoretische Informatik
Academic chair34352900 FG Big Data Engineering

Contact

OfficeTEL 8-1
Contact personBöhm, Matthias
E-mail addressmatthias.boehm@tu-berlin.de
Websitehttps://mboehm7.github.io/

Learning outcomes

Students are able to examine the inner workings of machine learning (ML) systems in detail and can apply the programming skills they have learnt to develop such a system from scratch themselves.
Students can create an inference engine for LLMs (Large Language Models) that utilises existing Hugging Face models for efficient, local generation. Students gain a sense of self-efficacy, enabling them to develop and influence systems for modern LLMs themselves.

Content

This module comprises a project, worked on by student teams and augmented by the following structure:
* Discussion rounds on design, implementation, tests, and experiments with a project mentor
* Design and implementation of an initial prototype including tests and documentation
* Short presentation of the initial prototype
* Experimental evaluation of the initial prototype
* Further development of the initial prototype into a final prototype, guided by the experimental results
* Attendance at presentations and giving a 15-minute presentation of the final prototype

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Machine Learning SystemsProject Winter semester[en]8 ISIS

Workload and credit points

Machine Learning Systems (Project)

Workload descriptionMultiplierHoursTotal
Attendance discussion rounds101 h10 h
Prototype implementation (including tests and documentation)1260 h260 h
Experiments and Performance Improvements175 h75 h
Presentation (Preparation and Attendance)115 h15 h
360 h

The workload of the module adds up to 360 hours. The module therefore comprises 12 credit points.

Description of teaching and learning methods

* Supervised, self-organized project work
* Setup and conduction of runtime experiments
* Presentation and defense of the results

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

#41078 Architecture of Machine Learning Systems

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingUngraded
Exam formatPortfolio examination
Type of portfolio examination100 points in total
LanguageEnglish

Test elements

NamePoints/WeightCategoryDuration/Extent
(Deliverable assessment) Project Implementation45practical≈200 hours
(Deliverable assessment) Design Document10written3 pages
(Deliverable assessment) Tests, source-code documentation, experiments30practical≈125 hours
(Deliverable assessment) Presentation of the final prototyp15oral30 minutes

Duration of the module

The following number of semesters is estimated for taking and completing the module: 1 semester(s).

This module can be started in the following semesters: Winter semester.

Maximum number of participants

The maximum capacity of participants is 20.

Registration procedures

Registration via the ISIS course.
Selection in accordance with the AllgStuPO during the first week of the semester

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

unavailable

Recommended literature

  • James Pan, Guoliang Li: A Survey of LLM Inference Systems. CoRR abs/2506.21901 (2025), https://arxiv.org/pdf/2506.21901

Assigned programs

This module version is used in the following programs:

Program / program versionSemester(s)Curriculum component
Computer Engineering
Computer Engineering (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering
Computer Science (Informatik)
Computer Science (Informatik) (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiete › Data and Software Engineering / Data and Software Engineering
Electrical Engineering
Electrical Engineering (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering
Information Systems Management (Wirtschaftsinformatik)
Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017
WS 2026/27Wahlpflichtbereich › Fachstudium Informatik › Data and Software Engineering
Computer Science (M. Sc.)
Information Systems Mangagement (M. Sc.)

Miscellaneous

Not specified