Platform Engineer - m/w/d

About the role

Platform Engineers at Langdock work on shared backend systems that many product features depend on. This includes the AI engine, queues, document processing, integrations, code execution, authentication, and billing. The job is to make these systems reliable and understandable enough that other engineers can build on them.

What you'll do

• Work on the AI engine that handles prompts and abstracts over providers such as OpenAI, Anthropic, Google, Azure, Bedrock, Mistral, and open-source models, including prompt caching, routing, and failover.
• Build and maintain the workflow runtime for executing reliably across agent steps, conditions, loops, structured-output extraction, and human-in-the-loop pauses.
• Optimize context-window usage to keep long conversations and uploaded files correct while controlling model costs.
• Develop a code execution service for running untrusted customer code with clear isolation of secrets, filesystem access, and tenant boundaries.
• Extend the integration layer for connecting Langdock to external services, supporting REST APIs and standards like Model Context Protocol (MCP).
• Design clear APIs, choose the right data models, handle failure cases, and add observability to shared systems.

What you'll need

• 3 to 6 years of experience building back-end systems that handle real load: queues, caches, databases, streaming pipelines, distributed schedulers.
• Strong in TypeScript and Node, opinionated about API design and abstractions.
• Infrastructure experience: Terraform, Kubernetes, cloud deployments, or operating services across AWS, Azure, or GCP.
• Working knowledge of the LLM ecosystem at a technical level: context windows, tool calling, streaming protocols, provider quirks, prompt caching.
• Security-first mindset with understanding of multi-tenant data isolation as a design constraint.
• Habit of adding metrics, traces, and structured logs from on-call experience.
• Heavy user of AI tooling in your own development workflow.

What they offer

• Top of market compensation with transparent levels and equity.
• Fully in-person engineering team in Berlin.
• Small temporary squads of 2 to 3 engineers around focused topics.
• Continuous deployment to production with AI-assisted code review.