Level: Senior

Job Field: Software, Product

Employment Type: Full Time

Contract Type: Permanent employment

Location: Berlin

Working Model: Hybrid, Onsite

Job Summary

In this role, you design agentic interfaces between customer applications and systems, develop modular agent skills, and orchestrate complex workflows in a data-driven environment.

Your role in the team

We're looking for a domain architect to shape the future of AI-powered, agentic-based workflow experiences across logistics, fleet, and mobility solutions.
The Agentic Domain Architect is responsible for designing and governing the agentic interfaces between customer applications, enterprise systems, and our domain-specific AI service and workflow layers.
This role sits at the intersection of domain architecture, agent design, product development and applied data science, working directly with customers, partners, presales and product team to translate complex customer workflows into domain-specific agent skills, context models, and interaction patterns.
You will define how agents understand domain reality, how they interact with customer systems, how workflows are decomposed into reusable skills, and how long-term agent memory and user interactions are converted into learning signals that continuously improve performance.
This is a hands-on role as part of the product team with strong ownership from concept design, implementation, and learning loop.
Design and own agentic integration patterns between customer applications, enterprise systems, and agent frameworks (APIs, events, MCP-style tool interfaces, schemas, contracts).
Define how agents invoke, coordinate with, and reason over external systems while respecting customer architecture, security, and governance constraints.
Act as the architectural authority on how agentic capabilities are embedded into real customer environments, not as standalone copilots.
Translate end-to-end business workflows into agent-compatible domain workflows, decomposed into modular, reusable agent skills.
Define skill boundaries, preconditions, outputs, confidence signals, and failure modes.
Ensure workflows support automation, human-in-the-loop, escalation, and explainability by design.
Align domain workflows with multi-agent or hierarchical agent orchestration models where needed.
Design domain-specific context models that combine operational data, spatial/temporal state (where relevant), user intent, and historical interactions.
Define what agents should remember, forget, summarize, or abstract over time (short-term, long-term, episodic memory).
Ensure context grounding is deterministic, auditable, and aligned with domain semantics rather than prompt-only heuristics.
Drive a data-centric approach to agent improvement by extracting signals from: Agent memory, User interactions, Workflow outcomes, Corrections and overrides.
Partner with data science to transform these signals into training data, evaluation metrics, and optimization strategies.
Influence model selection, grounding strategies, and reasoning approaches based on domain evidence rather than generic benchmarks.

This text has been machine translated. Show original

Our expectations of you

Education

Bachelor's or Master's degree in computer science, software engineering, cognitive/data science or a related field.

Qualifications

You are an architecture-first thinker who remains pragmatic, delivery-oriented, and comfortable operating in ambiguity and shaping new patterns rather than applying existing playbooks.
You have strong communication skills, able to align technical depth with business and operational context.
Strong background in domain or enterprise architecture, solution architecture, or complex system design.
Strong understanding of agentic AI concepts: agent skills, orchestration, grounding, memory, reasoning, tool use.
Ability to collaborate deeply with data science on datasets, signals, evaluation, and learning loops.
Comfort discussing trade-offs between deterministic logic, probabilistic reasoning, and learned behaviour.
Strong grasp of semantic models, schemas, and interface contracts.
Comfortable working in fast-paced, cross-functional, and highly technical environments.
Fluency in spoken and written English.

Experience

5+ years of experience designing workflow-centric systems (not just APIs or microservices), with several years focused on AI-driven systems.
Strong experience designing for complex workflows, ideally in logistics, fleet, mobility, automotive, or enterprise platforms.
Hands-on experience working with LLMs or agent frameworks in production contexts.
Experience integrating with customer systems (ERP, TMS, FSM, data platforms, event-driven architectures, etc.)
Experience collaborating with international and distributed teams across B2B/B2C context.

This text has been machine translated. Show original

What we offer

Innovative and modern technologies
Truly international team of fantastic & talented people from 60+ countries worldwide, working from strong tech hubs located in Europe, US and Asia and multiple smaller locations
A great work-life balance
Challenging problems to solve
Collaborative and encouraging colleagues
Opportunities to learn, grow and develop
Flexible working hours
Competitive salary plus bonus
Employee wellness programs and life-coaching sessions