AI Developer (m/w/d)

BeatSquares GmbH; Berlin; Hybrid; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Office in central Berlin

Remote days

Competitive salary

Equity option

Job summary

BeatSquares GmbH in Berlin is seeking an experienced AI product engineer to own LLM-powered features from prompt to editor. You will ship product-facing features, iterate quickly, and manage a multi-LLM pipeline across providers such as Anthropic, OpenAI, Gemini, and Fireworks/Kimi.

You will build eval loops, ensure traceability across LLM systems, and design human-in-the-loop workflows. A hybrid work setup with a Berlin office is offered, plus equity options.

Qualifications

• Demonstrated product instinct and speed: you ship working things and make pragmatic trade-offs.
• AI-native daily development (Claude, Cursor) as a real workflow, not a demo.
• Hands-on experience with LLM orchestration (function calling, agents, evaluation).
• You have built an eval loop, not just written prompts: baseline, iteration, measurable result.
• You have traced LLM behaviour in production (LangSmith or equivalent) and used it to find a real bug.
• You can explain when a deterministic pipeline is the better choice than an agent.
• Python, and the willingness to own the deployment of your own work.
• Fluent English

Responsibilities

• Build product-facing features across the stack, with a clear bias toward shipping and iterating.
• Work on our multi-LLM pipeline (Anthropic, OpenAI, Gemini, Fireworks/Kimi) and make deliberate calls on model selection, cost and latency.
• Build eval loops against real editorial output: define the baseline, iterate, and be able to show what measurably improved.
• Own traceability across our LLM systems, meaning per-step tracing and prompt provenance, so a bad output can be traced back to the call that produced it.
• Design human-in-the-loop agent workflows: agents propose, the newsroom decides. Nothing goes live autonomously.
• Prototype fast, harden afterwards, and ship your own work to production, including configuration, feature flags and scheduled jobs.
• Bring your own product ideas, rather than only working through tickets.

Skills

Product instinct

AI-native development

LLM orchestration

Eval loops

Python

English fluency

Tools

LangSmith

FastAPI

Frontend basics

Job description

Your mission

You own LLM-powered features end to end, from the prompt to what the editor sees, and you care whether the output actually gets published. You get ideas into working shape quickly instead of waiting for the perfect spec, and you stay with them until they hold up in production.

• Build product-facing features across the stack, with a clear bias toward shipping and iterating.
• Work on our multi-LLM pipeline (Anthropic, OpenAI, Gemini, Fireworks/Kimi) and make deliberate calls on model selection, cost and latency.
• Build eval loops against real editorial output: define the baseline, iterate, and be able to show what measurably improved.
• Own traceability across our LLM systems, meaning per-step tracing and prompt provenance, so a bad output can be traced back to the call that produced it.
• Design human-in-the-loop agent workflows: agents propose, the newsroom decides. Nothing goes live autonomously.
• Prototype fast, harden afterwards, and ship your own work to production, including configuration, feature flags and scheduled jobs.
• Bring your own product ideas, rather than only working through tickets.

Your profile

Must-have:

• Demonstrated product instinct and speed: you ship working things and make pragmatic trade-offs.
• AI-native daily development (Claude, Cursor) as a real workflow, not a demo.
• Hands-on experience with LLM orchestration (function calling, agents, evaluation).
• You have built an eval loop, not just written prompts: baseline, iteration, measurable result.
• You have traced LLM behaviour in production (LangSmith or equivalent) and used it to find a real bug.
• You can explain when a deterministic pipeline is the better choice than an agent.
• Python, and the willingness to own the deployment of your own work.
• Fluent English

Nice-to-have:

• Depth in FastAPI. We will also look at it if you have shown something comparable in another language.
• Enough frontend confidence to own a feature end to end.
• Experience with publishing or editorial workflows.
• German.

Why us?

• Direct collaboration with the founders and real influence on product and culture
• An AI-native working environment with first-class tools
• Flexible hybrid setup with an office in central Berlin and remote days
• Competitive salary and equity option
• Flat hierarchy, short paths and fast decisions

seniority: experienced
schedule: full-time
employmentType: permanent
Job location: Berlin, Rudi-Dutschke-Straße betahaus 23, 10969, DE