Staff AI Engineer — Agent Platform (all genders)

Free resume; Berlin; Hybrid; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Flexible remote setup

Generous vacation budget

Technical ownership of AI platform

Job summary

wingmaite is seeking a Staff AI Engineer to own the technical quality and direction of our agent platform. You will build features end to end, from the agent into the backend, with close collaboration with the CTO as a technical sparring partner.

You design agents, connect them to company knowledge, ensure reliability, track quality, and ship features end to end in a flexible remote setup. Collaboration with design, product and engineering is key.

Qualifications

• Shipped multi-step, tool-using LLM agents to production.
• Built evals and understanding of retrieval in AI systems.
• Fluent in Python and productive in TypeScript/Node (NestJS a plus).
• Proficient with PostgreSQL and data modeling.
• Uses AI coding tools such as Claude Code daily.
• Able to explain trade-offs with non-engineers.

Responsibilities

• Design the agents: plan, use tools and handle multi-step work.
• Connect agents to knowledge sources and decide content.
• Make answers reliable: cite sources and restrict visibility.
• Track quality: build evals, monitor costs and model choices.
• Ship end to end: ownership from agent to backend.
• Keep architecture consistent and document decisions with teams.

Skills

LLM agents in production

Evaluation & retrieval

Python

TypeScript/Node

Specification writing

German language

Tools

NestJS

PostgreSQL

Langfuse

Claude Code

AWS Bedrock

Vertex AI

Job description

Staff AI Engineer — Agent Platform (all genders)

Direct company application on www.arbeitnow.com . Zero third-party aggregator forms.

Job Description

wingmaite captures the knowledge companies never write down: who decides what, how work actually gets done, and why decisions were made. Our AI agents use that knowledge to answer questions and get work done.

We're looking for a Staff engineer to own the technical quality and direction of our agent platform. You'll build features end to end, from the agent into the backend. You won't manage people. You'll work closely with our CTO as a technical sparring partner.

What You'll Do

Design the agents: Decide how our agents plan, use tools and handle multi-step work, and where people need to step in. Build reusable components so each new use case doesn't need its own system.

Connect agents to company knowledge: Build how that knowledge reaches the agents, together with the people who decide what it should contain.

Make answers reliable: Agents should be correct, cite their sources, show people only what they're allowed to see, and know when not to act.

Track quality: Build evals, monitor quality and cost, and keep our model choices up to date.

Ship end to end: Build features from the agent through to the backend yourself.

Keep the architecture consistent: Set the patterns others build on, document decisions, keep specs current, and review designs with engineering, product and design.

How We Work

We build features as one team: design, product, engineering and AI together, from the first idea to production. You'll help shape a feature while it's still a problem and stay with it until it works for users. Agents depend on the knowledge behind them, so we build both as one system. We write decisions down and discuss disagreements openly.

What This Role Is Not

A management role, a prompt-engineering role, or an infrastructure or security role.

What We're Looking For

Must-Haves

You've shipped multi-step, tool-using LLM agents to production (LangGraph or similar)

You know when sub-agents help, how to build good evals, and why retrieval fails

Fluent in Python and productive in TypeScript/Node (NestJS is a plus)

PostgreSQL and data modeling

You use AI coding tools such as Claude Code every day

You write clear specs and can explain trade-offs to people who aren't engineers

Nice-to-Haves

None of these are required, but they'll help you get up to speed faster:

You've connected agents to tools and data through MCP

You've worked with knowledge graphs or other ways of modeling how people, work and information relate

You've run models in production on AWS Bedrock or Vertex AI

You've traced and debugged agents with LLM observability tools such as Langfuse

You speak German

Who You Are

You've set technical direction beyond your own work, and others build on your patterns

You start from what users need and what could go wrong, then choose the tools

You care whether the system still makes sense in a year

You're happy to do backend work when a feature needs it

You want influence through your work, not through a title

You like working with designers and product people

You enjoy technical debate and change your mind when the other argument is better

What We Offer

Flexible remote setup

Generous vacation & workation budget

Technical ownership of the platform at the core of wingmaite's product