Werkstudent*in AI Inference & Platform Engineering (m/w/d/x)

Telekom; Hamburg; On-site; EUR 17,000 - 25,000; Part time

Benefits offered by this job

Flexible working hours

Part-time option

Experience with NVIDIA GPU infra

Job summary

T-Systems International GmbH in Hamburg is seeking a dedicated working student for AI Inference & Platform Engineering to join our AI Foundation team. You will help develop, deploy, and test LLM inference services and build Python-based tools to automate model deployments.

You will work with Docker, Kubernetes, and modern LLM serving frameworks on NVIDIA GPU infrastructure, gaining hands-on experience in AI infrastructure and backend development while pursuing your studies.

Qualifications

• Pursuing a bachelor’s or master’s degree in computer science, AI, software engineering, or mathematics.
• Strong Python programming skills and practical software development experience.
• Basic knowledge of backend development, REST APIs, and modern software practices.

Responsibilities

• Assist in developing, deploying, and testing LLM inference services on the AI Foundation platform.
• Develop Python-based tools, scripts, and APIs to automate model deployments.
• Conduct performance benchmarks for LLMs and analyze latency, throughput, and resource usage.
• Collaborate on evaluating LLM serving frameworks and optimizing backend services and APIs.
• Assist in containerized app deployment with Docker and Kubernetes.
• Contribute to data pipelines and analyses to evaluate performance metrics.
• Participate in CI/CD automation and technical documentation.

Skills

Python

NumPy

pandas

scikit-learn

Git

Linux

REST APIs

CI/CD

English

Backend development

Docker

Kubernetes

FastAPI

vLLM

sGLang

Tensorrt-LLM

NVIDIA Dynamo

Education

Bachelor’s or Master’s in Computer Science / AI / Software Engineering / Mathematics

Tools

Docker

Kubernetes

FastAPI

vLLM

sGLang

Tensorrt-LLM

NVIDIA Dynamo

Job description

Job ID: 733424Werkstudent*in AI Inference & Platform Engineering (m/w/d/x)HamburgProfessionalWork-Study JobT-Systems International GmbHWorking student at TelekomDo you want to put the theory you have learned into practice and experience and help shape the digital world of tomorrow today? Then you've come to the right place! We can make and copy coffee ourselves. We are looking for working students like you who want to advance the connected world every day with team spirit and a willingness to innovate and perform!T-Systems International GmbHAt T-Systems, we offer our business customers the right system solutions for their digital business. With our portfolio, we ensure that digital transformation reduces complexity, saves costs and makes everyday work easier. Our focus is connectivity, digital, cloud & infrastructure as well as security - Let's power higher performance!About the positionWith the Industrial AI Cloud, T-Systems is developing one of the most powerful AI infrastructures in Europe. Based on cutting-edge NVIDIA GPU systems, including DGX B200 and B300, we enable companies to operate large language models (LLMs) and generative AI applications securely, scalably and with high performance.We are looking for a dedicated working student AI Inference & Platform Engineering (m/f/d/x) to join our AI Foundation team.You help us develop, deploy, and optimize LLM inference services on our Industrial AI Cloud. Together with experienced AI and platform engineers, you will work on scalable and powerful AI services for corporate customers.The position is aimed at students in computer science or related fields with good Python skills, initial experience in machine learning or backend development, and an interest in modern AI infrastructure.Your main tasks:We are looking for enrolled students to support our team in Hamburg from 01.01.2027 for at least 6 and a maximum of 24 months with up to 20 hours per week with the following tasks:Support in developing, deploying, and testing LLM inference services on the T-Systems AI Foundation platformDevelop Python-based tools, scripts, and APIs to automate model deployments and operational processesConduct performance benchmarks for LLMs and analyze latency, throughput, and resource utilizationCollaboration in the integration and evaluation of modern LLM serving frameworks such as vLLM, sGLang and NVIDIA DynamoDevelop and optimize backend services and APIs for AI applicationsHelping you deploy containerized applications with Docker and KubernetesDevelopment of data pipelines and analyses to evaluate performance and operational metricsInvestigation of optimization techniques such as KV caching, continuous batching, and efficient GPU usageCollaboration on automated tests, CI/CD pipelines, and technical documentationWorking with experienced AI engineers to integrate new AI models and technologiesThat's what you bring with youYou are studying a bachelor's or master's degree in computer science, artificial intelligence, software engineering, mathematics or a comparable degree programYou also have the following knowledge and skills:Good programming skills in Python and practical experience with software development, automation or data processingFirst practical experience in software development, machine learning, data engineering or backend development through professional activities, internships or own projectsKnowledge of Python libraries such as NumPy, pandas, scikit-learn or comparable frameworksBasic knowledge of backend development, REST APIs, and modern software development practicesExperience with Git, Docker, and Linux-based development environmentsBasic understanding of machine learning, model evaluation and performance benchmarkingAnalytical thinking, structured working methods and enjoyment of complex technical challengesPersonal initiative, ability to work in a team and interest in the development of modern AI technologiesGood English language skillsNice-to-haveExperience with Python backend frameworks such as FastAPIFirst points of contact with large language models, generative AI, or model inferenceBasic knowledge of LLM serving frameworks such as vLLM, sGLang, or Tensorrt-LLMKubernetes and container orchestration skillsExperience with CI/CD tools such as GitHub ActionsKnowledge of SQL, databases, and data pipelinesExperience with asynchronous Python programming, caching, or performance optimizationInterest in NVIDIA GPU technologies, distributed systems, and high-performance computingBasic knowledge of monitoring and observabilityWhat we offerCollaboration on one of Europe's largest AI infrastructure platformsInsights into cutting-edge NVIDIA GPU infrastructure, including DGX B200 and B300Practical experience with current LLM inference technologies such as vLLM, sGLang, NVIDIA Dynamo, and Tensorrt-LLMAbility to build skills in AI inference, GPU computing, Kubernetes, and productive AI systemsClose collaboration with experienced AI engineers, software developers and platform specialistsCollaboration on real AI services for corporate customersFlexible working hours that are compatible with your studiesAn innovative work environment with diverse learning and development opportunitiesThis position is also available on a part-time basis.Severely disabled people are given priority if they are equally qualified.https://www.xing.com/companies/deutschetelekomaghttps://www.linkedin.com/company/telekomJob BenefitsProfessional DevelopmentCollaboration on one of Europe's largest AI infrastructure platformsInsights into cutting-edge NVIDIA GPU infrastructure, including DGX B200 and B300Practical experience with current LLM inference technologies such as vLLM, sGLang, NVIDIA Dynamo, and Tensorrt-LLMAbility to build skills in AI inference, GPU computing, Kubernetes, and productive AI systemsClose collaboration with experienced AI engineers, software developers and platform specialistsCollaboration on real AI services for corporate customersInnovative work environment with diverse learning and development opportunitiesWork-Life BalanceFlexible working hours that are compatible with your studies