L

Langdock

Model-agnostic enterprise AI platform

Senior Platform Engineer

Platform EngineeringConfirmed live in the last 24 hours
Full-timeBerlin, Germany

About the Job

Requirements

  • Have 3 to 6 years of experience building and operating backend systems under real load.
  • Be strong in TypeScript and Node.js and comfortable with Kubernetes, Terraform, networking, databases, and queues.
  • Have strong platform design judgment and be able to define stable service boundaries and APIs while accounting for data integrity, tenant isolation, backward compatibility, partial failure, and safe rollout.
  • Be able to investigate underspecified systems problems, identify important invariants, choose where to go deep, and understand unfamiliar components and failure modes.
  • Be able to make systems observable, respond to failures, and turn incidents into lasting improvements.
  • Use AI tools effectively while remaining responsible for architecture and shipped changes.
  • Be able to independently investigate unfamiliar problems, design and ship solutions, and operate them in production.
  • Have an existing right to work in Germany.

Responsibilities

  • Own shared platform capabilities as internal products, defining interfaces for other teams and remaining accountable for reliability, evolution, and operation.
  • Turn platform capabilities such as model access, agent execution, authorization, queues, integrations, document processing, and sandboxed compute into stable, reusable building blocks with clear contracts.
  • Own a service from design through long-term operation, including defining its API and failure behavior, planning migrations, implementation, deployment, observability, and production incident response.
  • Work with Systems Engineers when a service requires a new underlying mechanism while remaining accountable for the service boundary and lifecycle.
  • Contribute to durable agent-runtime work, including separating runtime from product-specific state, designing recoverable durable runs, reconstructing context deterministically, compaction, and prompt-cache efficiency.
  • Build the Model Gateway, including provider adapters, routing, rate limits, bounded fallback, streaming safety, usage tracking, and a control plane.
  • Move selected capabilities from a TypeScript monolith into independently operated services using Protobuf and gRPC contracts in a Bazel monorepo.
  • Contribute to authorization-service migration using an outbox, shadow comparisons on production traffic, and consistency tokens.
  • Make authentication, token refresh, rate limits, approvals, outbound network safety, and tool execution consistent across REST APIs, Model Context Protocol, and agent-to-agent communication.
  • Define the execution API, lifecycle, permission model, resource budgets, and operational boundary for code execution as a shared service, partnering with Systems Engineers on isolation and scheduling mechanisms.
  • Build production confidence through reusable load testing for HTTP, gRPC, and streaming workloads; structured logging that excludes user content and personally identifiable information; and online PostgreSQL changes.
  • Own an assigned platform area’s interface and production operation.
  • Own shipped changes in production and lead fixes when they fail.
  • Work with a squad to own its roadmap, prioritization, technical decisions, and production operation.
  • Use design documents to make architectural boundaries, tradeoffs, failure modes, migrations, and rollouts explicit.
  • Invest in observability, migration tooling, automated recovery, and runbooks to reduce recurring manual maintenance.

Desired Qualifications

  • Experience with Go is useful, and willingness to work in Go is important.
  • Familiarity with most of the stated technology stack, with an ability to pick up the rest quickly.

About the Company

Langdock

Model-agnostic enterprise AI platform

Langdock provides an enterprise AI platform that lets companies securely access and deploy multiple language models from providers like OpenAI, Anthropic, Google, and Meta, avoiding vendor lock-in. It uses a model-agnostic application layer with features such as an employee chat interface, customizable AI assistants, enterprise search, and a unified API, plus support for multi-step workflows and integrations with tools like Slack, Google Drive, and Confluence. Unlike platforms tied to a single provider, Langdock emphasizes governance and security with GDPR compliance, ISO 27001, SOC 2 Type II, and EU data hosting. Its goal is to help organizations adopt AI tools productively while maintaining data security and regulatory compliance.

Company size
51-200
Company stage
Seed
Total funding
$3.1M
Headquarters
Berlin, Germany
Founded
2023

Recently Posted Jobs

Explore more opportunities at Langdock

See more jobs