Job
- Level
- Experienced
- Location
- Kerstenhausen
- Working Model
- Hybrid, Onsite
- Job Field
- Embedded, Back End
- Employment Type
- Full Time
- Contract Type
- Permanent employment
Job Summary
In this role, you will develop AI systems, design agent architectures, and integrate ML concepts into a SaaS application while also managing and optimizing their operations.
Job Technologies
Your role in the team
- You develop our AI systems - from agent-based assistants to a platform where our clients can assemble their own agents, tasks, and workflows.
- The role is hands-on: You write code, design agent architectures, and also operate what you build yourself.
- In this role, you work at the point where it is decided whether an AI feature impresses only in the demo or functions reliably in the daily operations of our clients.
- You work closely with backend development, product, and [other interfaces], actively contributing your insights to architecture and product decisions.
- (Further) development of our agent-based AI assistant - from conception through implementation to operation.
- Co-developing a dynamic multi-agent system in which customers can create and configure their own agents, tasks, and workflows.
- Design of agent systems whose behavior and quality are controllable and traceable - including guardrails, permission concepts, and human-in-the-loop mechanisms.
- Development of systematic evaluation strategies: You verify whether changes to prompts, tools, and agents are genuinely improvements — not just perceived as better.
- Integration of AI and ML concepts into an existing, mature SaaS application - including everything that comes with it: data model, permissions, performance, costs.
- Operations and Optimization: Observability, Tracing, Latency, Cost, and Stability Optimization.
This text has been machine translated. Show original
Our expectations of you
Qualifications
- Very good conceptual understanding of how LLMs work — and their limitations.
- Understanding further ML concepts and how to meaningfully integrate them into business logic.
- In-depth understanding of tokenization/tokens, embeddings, and context windows.
- Understanding of Vector Search, Retrieval, and Re-ranking (RAG).
- Knowledge of hallucinations, context bloat, and other common error modes – including strategies to identify and mitigate them.
- Understanding of A2A (Agent2Agent Protocol), MCP (Model Context Protocol), and Human-in-the-Loop.
- Knowledge of security risks of LLM and agent systems (including prompt injection, tool misuse, data leakage).
- Understanding Context Engineering - targeted selection, preparation, and management of what actually enters the Context Window.
- Understanding of multi-agent architectures, agent handoffs, and orchestration (A2A).
- Ability to develop systematic evaluation strategies for agents and other ML components.
- Understanding of quality metrics and evaluation methods - e.g., LLM-as-a-Judge, Task Success Rate, Tool Call Accuracy.
- Testing and versioning of agents, prompts, and tool definitions.
- Optimization of quality, stability, latency, and costs.
- Genuine interest in testing and deploying various AI and ML concepts within an existing SaaS application.
- Pragmatism: You know the difference between an impressive demo and a system that still does the right thing even on the 10,000th run.
Experience
- Experience with Tool Calling and Structured Outputs.
- Experience in Prompt Engineering - formulation, structure, and management of individual model requests.
- Experience in Harness Engineering - designing the environment in which an agent operates: tools, feedback loops, control flow, and termination conditions.
- Experience with guardrails and permissions, especially RBAC and ABAC in user-centric SaaS systems.
- Experience or solid understanding of asynchronous processing, background jobs, and task queues.
This text has been machine translated. Show original
What we offer
- There is the possibility to work remotely, hybrid, or on-site.
- Structured onboarding into the product, processes, and testing procedures.
This text has been machine translated. Show original
Topics You Will Work On
Job Locations
About Your Employer
conmeet GmbHconmeet GmbH
conmeet GmbH, based in Borken, Germany, is a modern company focused on developing digital control system solutions for craft and construction businesses. Their cloud-based software platform integrates various business processes such as order processing, project management, and controlling, primarily targeting medium-sized companies. Since its founding in 2023, the company has been enhancing its platform with AI-driven features to meet industry demands.
Description
- Company Type
- Startup
- Working Model
- Hybrid, Onsite
- Industry
- Construction, Real Estate, Building Services
AI Engineer - Agentic Systems & Backend Engineering
- Location
- Kerstenhausen
- Working Model
- Hybrid, Onsite
- Diversity
- Open for all genders
