Role Overview

As a Senior GenAI Engineer, you will be a founding member of our generative AI efforts, moving beyond PoCs to deploy enterprise-grade, agentic solutions. You will design and implement highreliability systems that support engineering, manufacturing, and global business workflows. This role is ideal for a hands-on expert who balances deep NLP technicality with a passion for building robust, hallucination-resistant architectures.

Key Responsibilities

1. Knowledge-Centric AI & NLP Development

• Hybrid Knowledge Systems: Design and maintain enterprise knowledge bases using a combination of Vector stores and Knowledge Graphs to ensure deep semantic grounding.

• LLM Optimization: Fine-tune and adapt LLMs using instruction tuning and parameter-efficient techniques (PEFT) for specialized industrial domains.

• Intelligent Ingestion: Build advanced Python pipelines for document understanding, structured data extraction, and entity normalization from complex technical documentation.

• Graph Integration: Bridge the gap between unstructured text and structured data by integrating Knowledge Graphs into RAG workflows to eliminate hallucinations.

2. Agentic Systems & Orchestration

• Autonomous Workflows: Architect multi-agent systems capable of reasoning, tool-usage, and iterative execution/validation loops. intern | internal

• System Integration: Enable agents to securely interact with Rosenberger’s internal APIs, ERPs, and engineering databases.

• Scalability: Define maintainable orchestration standards for deploying agents in highconcurrency enterprise environments.

3. Reliability, Evaluation & Azure Infrastructure

• Quality Guardrails: Implement rigorous evaluation frameworks to measure factual accuracy, latency, and cost-efficiency.

• Hallucination Control: Develop active grounding techniques and consistency checks to ensure production-grade reliability.

• Azure AI Cloud: Leverage Azure AI Foundry and Azure OpenAI to deploy and manage the full lifecycle of GenAI solutions across global locations.

Required Qualifications

• Education: Bachelor’s or Master’s in Computer Science, AI, Machine Learning, or a related technical field.

• Experience: 5+ years in Software Engineering or ML, with a significant focus on NLP and production-grade AI.

• Technical Stack:

- Expert-level Python and experience with frameworks like LangChain, LlamaIndex, or AutoGen. 

- Deep understanding of RAG architectures and vector database management.

- Proven ability to extract structured information from complex, semi-structured documents (PDFs, technical manuals).

• Expertise: Solid grasp of LLM failure modes, benchmarking (e.g., RAGAS, G-Eval), and mitigation strategies.

Preferred Differentiators

• Graph Mastery: Experience with Graph databases (Neo4j, etc.) and hybrid symbolic+neural approaches.

• Azure Ecosystem: Hands-on experience with Azure AI Foundry and enterprise security/governance.

• Industrial Context: Background in manufacturing, digital engineering, or product lifecycle management (PLM) data.

• Operational Excellence: Familiarity with LLMOps (monitoring, observability, and versioning for LLMs). What We Offer

• Impact: Transition from demos to high-stakes, "real-world" industrial AI applications.

• Global Collaboration: High visibility with our German HQ and international teams.

• Career Trajectory: A clear path toward Lead Engineer or AI Architect roles within our growing Competence Center