AI Engineer (m/f/d)

Vectoryx USA Inc.; Berlin; Vor Ort; EUR 90.000 - 130.000; Vollzeit

Zusammenfassung

Vectoryx USA Inc. in Berlin is building an AI-native claims platform, with agents that read cases, decide next steps, and communicate with all parties.

You will own the agentic pipeline and the evaluation and feedback systems, and, as a full-stack engineer, ship clean internal UI when needed. We value empiricism, ownership, and hands-on work in a small, fast-moving team.

Join a team that ships reliable AI systems and continuously improves with real-world signals and thoughtful design.

Qualifikationen

• 3+ years in software engineering with hands-on LLM/agent work.
• Strong Python skills and ability to ship full-stack features.
• Experience building evaluation and feedback systems for AI products.
• Comfort with ambiguity and ownership in a small team.

Aufgaben

• Own the agentic pipeline and evaluation/feedback systems.
• Build systems that remain reliable when the model is unavailable.
• Ship clean internal UI when needed and collaborate across the stack.
• Work empirically with evals to measure improvements over time.

Kenntnisse

Python

LLM/agent systems

Full-stack engineering

UI development

Empirical evals

Tools

LangGraph

LangChain

Langfuse

RAG design

Jobbeschreibung

We're building an AI-native claims operation. Our thesis: the moat isn't the model — it's the system around it that makes AI reliable enough to trust with real operational work. Building that system is this role. We're an agile, senior team automating residential property claims, with agents running live cases today. You'll own the agentic pipeline and the evaluation and feedback systems that make it measurably good — and, being full-stack, the interfaces where humans work alongside it.

• Our multi-agent pipeline (LangGraph, LangChain) — the agents that read a claim, decide the next step, and communicate with every party
• Context and prompt engineering — getting the right knowledge to the agents and keeping their behaviour reliable
• The evaluation and testing systems that let us measure agent quality and ship changes with confidence — this is the actual product
• The feedback systems that turn real-world signals into measurable improvement over time
• Model routing and experimentation across providers
• The full-stack surfaces where our team reviews and works with the agents

Your profile

• Have 3+ years in software engineering, with real hands-on LLM/agent work — not just calling an API, but building systems that stay reliable when the model doesn't
• Are strong in Python and comfortable enough across the stack to ship a clean internal UI when it's needed
• Think empirically about AI: you reach for evals, not vibes, and you know "it works on my three examples" isn't evidence
• Have built — or badly wanted to build — proper evaluation and feedback systems for an LLM product
• Are comfortable with ambiguity and high ownership in a small team

Nice to have

• Experience with LangGraph/LangChain, Langfuse, or agent-evaluation tooling
• Prompt/context engineering at production scale
• RAG, retrieval, or knowledge-base design
• Insurance, fintech, or another regulated domain
• German (helpful, not required — we work in English)