Job
- Level
- Experienced
- Location
- Osnabrück
- Working Model
- Hybrid, Onsite
- Job Field
- Software, Data
- Employment Type
- Full Time
- Contract Type
- Permanent employment
- Salary
- 3.500 to 5.000€ gross/month
Job Summary
In this role, you will develop AI agents and multi-agent workflows, integrate orchestration frameworks, and ensure the reliability of systems within a containerized IT environment.
Job Technologies
Your role in the team
- As a tech company with locations in Cologne and Osnabrück, we have been specialists in "Interactive Digital Signage" and "Mobile Solutions" at the Point of Sale and Point of Interest for over 15 years, as well as experts in all projects related to digital transformation.
- We are looking for a Software Engineer - Agentic AI Systems (m/f/d) to join our dynamic team at the Osnabrück location as soon as possible in full-time.
- Design and development of production-ready AI agents and multi-agent workflows for real-world use cases - from role allocation and tool utilization to planning and reasoning loops, as well as memory and state management across multiple agents.
- Selection and integration of agent orchestration frameworks and interop protocols (e.g., LangGraph, CrewAI, AutoGen, Semantic Kernel, PydanticAI, MCP, vendor agent SDKs) and their connection to existing REST APIs, event streams, and data pipelines.
- Meeting and documenting architecture decisions (ADRs) as well as ensuring non-functional requirements (reliability, cost and latency control, traceability of agent decisions).
- Instrumenting agent behavior for tracing, evaluation, guardrails, and reproducibility of non-deterministic runs.
- Expansion of our event-driven Python data platform (FastAPI services, pipeline orchestration, event bus, relational and vector storage, object storage) to include the interfaces required by agents - new event types, callable tools, retrieval endpoints, human-in-the-loop touchpoints.
- Collaboration across disciplinary boundaries - from Data Engineering through Backend (Python / FastAPI) to DevOps - for the operational deployment of agent systems in container environments (Docker Compose in production; Kubernetes experience is a plus).
- Creation of high-quality, testable code - independently and with AI support (agentic coding tools) - as well as code and pull request reviews.
- Evaluation and monitoring of agent behavior (tracing, guardrails, error handling of non-deterministic behavior).
- Independent problem analysis, troubleshooting, and deployments (CI/CD, container, and cloud deployments).
- Responsibility for operational security and stability of agent systems (troubleshooting in production, release management) - in our ISO 27001 certified environment.
- Close collaboration with Product Owners, stakeholders, and clients to clarify use cases and feasibility.
- Active participation in the agile process (task refinement, effort estimations, sprint planning).
- Knowledge transfer within the team on agentic AI practices and tools.
This text has been machine translated. Show original
Our expectations of you
Education
- Successfully completed studies in Computer Science, Business Informatics, or a comparable degree program - or a completed apprenticeship in the field.
Qualifications
- Loyalty and integrity.
- Enjoyment of teamwork and collaborative work.
- Desire for autonomous and self-organized work.
- Understanding common LLM application patterns: prompting, tool / function calling, RAG, context and memory management.
- Good programming skills in Python (FastAPI or comparable asynchronous web framework); knowledge of TypeScript (Angular / React) is an advantage.
- Solid knowledge in designing Web APIs (REST, OpenAPI, versioning, contract discipline).
- Solid data engineering fundamentals (SQL / PostgreSQL, relational data modeling, schema migrations, ETL / ELT concepts).
- In-depth knowledge of vector databases and retrieval strategies (pgvector, Qdrant, Weaviate, or comparable) - essential for our retrieval and agent-memory layers.
- Awareness of the peculiarities of non-deterministic systems (testing, evaluation, observability of agent behavior).
- Confidently working in an ISO 27001 certified environment - handling secrets, audit trails, tenant-specific data separation.
- High comprehension, solution-oriented, and efficient working style.
- Good German and English language skills, both written and spoken.
Experience
- Several years of professional experience in software development as well as practical experience with LLM-based applications or agent systems in production deployment.
- Direct experience with integrating hosted LLM provider APIs (e.g., Anthropic, OpenAI, Google, Mistral) in production environments – including error handling, rate-limit resilience, as well as cost and latency management.
- Practical experience with at least one agent / orchestration framework (e.g., LangGraph, CrewAI, AutoGen, Semantic Kernel, PydanticAI, vendor SDKs, or comparable in-house developments).
- Practical experience with the Model Context Protocol (MCP) - setting up or using MCP servers to provide agent tools.
- Practical experience with a pipeline / workflow orchestration tool (Dagster, Airflow, Prefect, Temporal, or comparable) - the category is more important than the specific product.
- Practical experience with event-driven architectures and stream / queue systems (Redis Streams, Kafka, NATS, RabbitMQ or comparable).
- Experience with modern DevOps practices and tools (Git, CI/CD, Docker, ideally Kubernetes).
- Experience with cloud computing providers such as STACKIT, AWS, or Microsoft Azure – ideally with deployments under EU data hosting.
This text has been machine translated. Show original
What we offer
- Flexible working hours.
- Option for hybrid working.
- Exciting and challenging projects.
- Dynamic and agile work environment.
- Attractive salary package.
- Space for personal development and growth.
This text has been machine translated. Show original
Benefits
Work-Life-Integration
Topics You Will Work On
Job Locations
About Your Employer
Newroom Media Gmbh
We advise our customers professionally and implement creative concepts together with them. Our services are individual and tailored to the needs of our customers. We use innovative technologies to perfect our work.
Description
- Company Type
- Digital Agency
- Working Model
- Hybrid, Onsite
- Industry
- Internet, IT, Telecommunication
Software Engineer - Agentic AI Systems
- Salary
- 3.500 to 5.000€ gross/monthEstimated net salary based on the gross salary in the job ad using tax class I.2.333 to 3.130 € net/month · Tax class I
- Location
- Osnabrück
- Working Model
- Hybrid, Onsite
- Diversity
- Open for all genders
