AI / ML Engineer - Agentic AI ( m/f/d)

Rohde & Schwarz GmbH & Co.; Dresden; Hybrid; EUR 70,000 - 90,000; Full time

Job summary

Rohde & Schwarz GmbH & Co. in Dresden, Germany, is seeking an AI systems engineer to design agent-based AI systems from idea to production. You will architect agent structures, model harnesses, and strategies for context management while aligning with user needs.

You will implement retrieval-augmented generation, vector search, and multi-stage orchestration with tool calling and MCP integrations, ensuring robust monitoring and handling of failure modes.

Responsibilities

• Design agent architectures, model harnesses, prompt strategies, and context management for agent-based AI systems.
• Implement retrieval-augmented generation, vector search, and multi-stage orchestration with tool calling and MCP integrations.
• Evaluate generative behavior, security, and failure modes such as hallucinations, and establish monitoring and countermeasures.
• Build reproducible evaluation pipelines and conduct metric-driven experiments.
• Transition solutions into production using MLOps and software engineering practices while aligning with users and stakeholders.
• Stay up to date with state-of-the-art foundation models and agentic AI and evaluate their platform potential.

Job description

Introduction

You design agent-based AI systems that make a real difference from the idea stage to actual implementation.

Tasks

• You design agent architectures, model harnesses, prompt strategies, and context management for agent-based AI systems.
• You implement retrieval-augmented generation, vector search, and multi-stage orchestration with tool calling and MCP integrations.
• You evaluate generative behavior, security, and failure modes such as hallucinations, and establish monitoring and countermeasures.
• You build reproducible evaluation pipelines and conduct metric-driven experiments.
• You transition solutions into production using MLOps and software engineering practices while remaining closely aligned with users and stakeholders.
• You stay up to date with the state of the art in foundation models and agentic AI and evaluate their potential for use on the platform.