Senior Backend Engineer, Workflow Orchestration, Temporal, Saga, Event Sourcing, Agentic AI, Remote
Llamazing Digital Engineering GmbH
Ansprechpartner: Björn Froese
BerlinBrandenburg, Deutschland
Endkundenprojekt
ITJavaDistributed ComputingTypeScriptWorkflowsWorkflow-Management-SystemeGoogle CloudBackendEvent Driven ArchitectureApache KafkaEvent-SourcingGolangMicroservicesBeschreibung
For agentic AI projects in industrial manufacturing in the DACH region, we are looking for experienced backend engineers for distributed systems (m/f/d) to join our expert pool. The work is 100% remote, and we welcome applications from anywhere in the world.
A typical project looks like this:
Starting point
A manufacturing company wants to handle production disruptions with an agentic workflow. When a machine fails, AI agents gather information from MES, production planning, maintenance and documentation, evaluate options (e.g. wait for the repair or move orders to an alternative machine) and present them to the responsible roles for approval. Only after human approval are the maintenance order and the rescheduling executed in the target systems. Decision-relevant figures come from traceable rules, not from the language model; every step can be interrupted and resumed and is fully logged. The solution runs on Google Cloud with Temporal as workflow engine. You own the core: the case as a state machine that can wait hours for approvals, resume after crashes and cleanly compensate partial failures.
Responsibilities
- Implement the case as an explicit, deterministic workflow: state model, timers, signals for human approvals, escalation
- Encapsulate side effects: every tool and model call as its own activity, child workflows per agent with a bounded number of steps
- Enforce idempotency: business action keys, optimistic locking via version stamps, retries without duplicates
- Handle partial execution following the saga pattern (compensation or an explicitly reported open state)
- Secure and test resumption and replay (worker restarts, fault injection, reproducibility for the same data state)
- Define interfaces to the approval backend, rule engine and simulated or real target systems together with agent and integration engineers
- Help shape the operation of Temporal (self-hosted or Temporal Cloud), including namespace authorization
- Document decisions and limits and hand over to the team
Must have
- At least 7 years of backend development experience, including at least 3 years with distributed systems in production
- Hands-on experience with at least one workflow or orchestration engine for long-running processes (e.g. Temporal, Cadence, Camunda/Zeebe, AWS Step Functions) or with self-built saga or event sourcing solutions
- Solid command of idempotency, retry strategies, compensation and consistency across system boundaries
- Strong skills in Go, Java, TypeScript or Python and automated testing
- Fluent English
- At least 4 hours of daily overlap with Central European Time (CET)
Nice to have
- Temporal in production (determinism, workflow versioning, replay tests)
- Experience with LLM applications or agent frameworks (e.g. LangGraph, OpenAI Agents SDK)
- Google Cloud (Cloud Run, Cloud SQL, Pub/Sub), Terraform
- Experience in manufacturing, logistics or fintech
- Experience working in agile, distributed teams
- German language skills
Terms
- Location: 100% remote
- Duration: typically 4 to 6 months, extension possible
- Workload: 80 to 100 percent
- Start: depending on the project, from Q1 2027
- Contract: freelance, invoicing in EUR
Application
Please answer briefly:
- Which system with long-running workflows or sagas did you most recently build in a leading role (engine, domain, your role, scale)?
- How do you prevent a write action from being executed twice or not at all after a crash in the middle of a process?
- What is your hourly rate in EUR, where are you based (country and time zone), and when are you available?
In email communication please always include the project ID of this ad. Please do not call unless an appointment has been arranged.