Jobs / T-Mobile
Werkstudent*in AI Inference & Platform Engineering (m/w/d/x)
T-Mobile · Hamburg, HH, Deutschland
Hamburg, HH, DeutschlandPart timeOnsite
Remuneration
Not specified
Location
Hamburg, HH, Deutschland
Visa sponsorship
Not specified
Job summary
Support the development, deployment, testing, and optimization of LLM inference services on an industrial AI cloud powered by NVIDIA GPU systems, helping deliver scalable AI applications for corporate customers. The work includes building Python tools, APIs, and backend services; benchmarking latency, throughput, and resource use; integrating serving frameworks such as vLLM, sGLang, and NVIDIA Dynamo; and contributing to containerized deployments, data pipelines, tests, and CI/CD.
Benefits
Professional development in AI inference, GPU computing, and KubernetesExposure to NVIDIA DGX B200 and B300 infrastructureCollaboration with AI engineers, software developers, and platform specialistsFlexible working hours compatible with studies
Qualifications
- Currently enrolled in a bachelor's or master's program in computer science, artificial intelligence, software engineering, mathematics, or a related field
- Good Python programming skills and practical experience with software development, automation, or data processing
- Initial practical experience in software development, machine learning, data engineering, or backend development through work, internships, or projects
- Knowledge of NumPy, pandas, scikit-learn, or comparable libraries
- Basic knowledge of backend development, REST APIs, and modern software practices
- Experience with Git, Docker, and Linux development environments
- Basic understanding of machine learning, model evaluation, and performance benchmarking
- Good English skills
Responsibilities
- Develop, deploy, and test LLM inference services on an AI platform
- Build Python tools, scripts, and APIs to automate model deployments and operations
- Benchmark LLM latency, throughput, and resource utilization
- Integrate and evaluate LLM serving frameworks such as vLLM, sGLang, and NVIDIA Dynamo
- Develop and optimize backend services and APIs for AI applications
- Deploy containerized applications with Docker and Kubernetes
- Build data pipelines and analyze performance and operational metrics
- Investigate KV caching, continuous batching, and GPU utilization optimizations
- Contribute to automated tests, CI/CD pipelines, and technical documentation
- Help integrate new AI models and technologies
Skills
DockerDynamoDBGitGitHubGitHub ActionsKubernetesLinuxPythonREST
Degrees
Currently pursuing a bachelor's or master's degree in computer science, artifici
Languages
English
Work schedule
Up to 20 hours per weekFlexible hours compatible with studies
Industry
AI infrastructureCloud computing
Contract length
6 to 24 months
Relocation
No