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

• Own 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 across model deployments
• Build and maintain the workflow runtime that executes reliably across agent steps, conditions, loops, structured-output extraction, human-in-the-loop pauses, and actions across hundreds of integrations
• Optimize context-window usage for long conversations, uploaded files, and tool calls while keeping model costs under control
• Develop a code execution service for running untrusted customer code with clear isolation of secrets, filesystem access, outbound network access, and tenant boundaries
• Build a flexible integration layer for connecting Langdock to external services, including REST APIs and industry standards like Model Context Protocol (MCP) and agent-to-agent (A2A) communication
• Design clear APIs, choose the right data models, handle failure cases, write tests for important invariants, and add useful observability

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, with opinions about API design, abstractions, and where boundaries should sit
• Some infrastructure experience: Terraform, Kubernetes, cloud deployments, networking, 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
• Habit of adding metrics, traces, and structured logs because you have been on call before and know you will need them
• Security-first mindset with multi-tenant data isolation as a design constraint
• Very driven with high standards, moving fast without needing to be pushed
• Heavy user of AI tooling in your own development workflow, already compounding your output with AI

What they offer

• Top of market compensation with transparent levels and equity included in all roles
• Fully in-person engineering team working from Berlin office (Greifswalder Str. 212)
• Opportunity to work on systems powering 6,000+ companies using Langdock daily