Master's Thesis Expert-in-the-Loop AgentOps/LLMOps Pipeline for Systems Engineering Process Agents(m/w/x)

Beschreibung

You will bridge the gap between AI and systems engineering by developing an AgentOps pipeline that integrates expert feedback to refine LLM outputs and improve requirements derivation.

Anforderungen

• •Solid programming skills, preferably in Python
• •Experience with C++/Java is a plus
• •Fundamental knowledge of machine learning / AI
• •Knowledge of LLMs, prompt engineering, RAG
• •Basic understanding of software engineering concepts
• •Basic understanding of cloud development
• •Analytical skills for experiments and metrics
• •Ability to work independently and document
• •Interest in operationalising AI agents
• •Experience with fine-tuning LLMs is advantageous
• •Interest in systems engineering processes
• •German skill >B1

Aufgaben

• •Review literature on MLOps, LLMOps, and AgentOps
• •Design an open-source AgentOps pipeline for systems engineering
• •Implement the pipeline with expert-in-the-loop feedback
• •Compare context engineering and fine-tuning adaptation strategies
• •Derive subsystem requirements and test cases
• •Measure precision, recall, and semantic correctness
• •Analyze expert corrections and cost-benefit metrics
• •Quantify the value of expert feedback for improvement

Tools & Technologien

Benefits