Werkstudent*in AI Inference & Platform Engineering (m/w/d/x)
Core
Supporting the development, deployment, and optimization of LLM inference services on the Industrial AI Cloud platform.
Role type
Student AI Inference & Platform Engineer
Builds
Scalable and performant AI services for enterprise customers
Domain
Cloud Infrastructure & Generative AI
Deliverable
production ML models
Required skills
Python, Machine Learning, Backend Development, REST APIs, Git, Docker, Linux, Performance Benchmarking
Preferred skills
FastAPI, LLM Serving Frameworks (vLLM, SGLang, TensorRT-LLM), Kubernetes, CI/CD, SQL, Asynchronous Programming, GPU Computing
Technologies
NVIDIA DGX B200/B300, vLLM, SGLang, NVIDIA Dynamo, TensorRT-LLM, Docker, Kubernetes, GitHub Actions
Responsibilities
Develop and test LLM inference services; Build Python tools for model deployment automation; Conduct performance benchmarks for LLMs; Integrate and evaluate LLM serving frameworks; Develop backend services and APIs; Manage containerized applications; Build data pipelines for metrics analysis; Optimize inference techniques (KV-Caching, Continuous Batching); Collaborate on CI/CD pipelines and documentation.
Seniority
Student (Part-time)