SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
GetYourGuide is building an internal agentic platform called Midnight Clue that enables product and engineering teams across the company to define context and delegate work to AI agents. As a Senior Software Engineer on this platform team, you will design and build core features and tooling that other engineers depend on.
Your responsibilities include:
- Design and build core features and tooling of the Midnight Clue agentic platform, enabling teams to define context and delegate work to agents
- Own the evaluation and observability layer: tracing, quality metrics, offline and online evaluations, and feedback loops that tell teams whether their agents are improving or degrading in production
- Shape the end-to-end user experience from context definition through testing, monitoring, and optimization of agentic workflows, with guardrails built in by default
- Drive architectural decisions for the platform, write RFCs, and partner with infrastructure and application teams to ensure alignment with GetYourGuide's broader systems
- Raise the bar for the team through code review, mentoring, pairing, and serve as a go-to technical voice for agent development across the organization
GetYourGuide is a travel experiences marketplace connecting millions of people with unique activities worldwide. The company operates from Berlin HQ with offices globally including New York and Bangkok.
Requirements:
- 6+ years of software engineering experience with a track record of building and operating platform-level or developer-facing systems that other engineers depend on
- Strong hands-on skills in TypeScript and Go, with sound judgment about when to use each
- Solid foundations in distributed systems, APIs, and cloud-native deployment (Kubernetes or similar)
- Practical production experience building with LLMs: prompt and tool orchestration, retrieval, agent loops, and understanding cost, latency, and reliability trade-offs
- A measurement mindset: experience building or running eval pipelines, tracing or monitoring for systems, and ability to explain what "good" looks like with data
- Ability to lead technically without a title: clear communication in writing and in person, ability to influence decisions across teams, and help others level up
Preferred qualifications:
- Experience with LLM observability or evaluation tooling (e.g., Datadog LLM Observability, LangSmith, Braintrust, OpenTelemetry-based tracing)
- Familiarity with agent protocols and frameworks such as MCP, and experience building SDKs or CLIs that other developers adopt
- Background in security, guardrails, or policy enforcement for AI systems (prompt injection defense, PII handling, permissioning)
- Prior work on an internal platform or DevEx team where adoption and developer satisfaction were success metrics
