Job
- Level
- Experienced
- Job Field
- Software, Data
- Employment Type
- Full Time
- Contract Type
- Permanent employment
- Location
- Berlin
- Working Model
- Hybrid, Onsite
Job Summary
In this role, you will develop end-to-end AI features, optimize LLM systems, implement human decision processes, and rapidly prototype innovative tools for editorial work.
Job Technologies
Your role in the team
- 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 quickly, then harden it, and deploy your own work to production, including configuration, feature flags, and scheduled jobs.
- Bring your own product ideas, rather than only working through tickets.
This text has been machine translated. Show original
Our expectations of you
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.
- 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
- Depth in FastAPI. We will also look at it if you have shown something comparable in another language.
- Genügend Frontend-Sicherheit, um eine Funktion von Anfang bis Ende zu übernehmen.
- German.
Experience
- Hands-on experience with LLM orchestration (function calling, agents, evaluation).
- Experience with publishing or editorial workflows.
This text has been machine translated. Show original
What we offer
- 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
This text has been machine translated. Show original
Topics You Will Work On
Job Locations
About Your Employer
BeatSquares
BeatSquares is an emerging company based in Berlin that focuses on developing AI-driven software for media organizations. The team assists local and regional newsrooms in distributing journalistic content more effectively and optimizing it for various channels. With an emphasis on LLM-supported workflows and automated content formats, BeatSquares provides solutions for quality assurance in the editorial context.
Description
- Company Type
- Startup
- Working Model
- Hybrid, Onsite
- Industry
- Media, Publishing
AI Developer
- Location
- Berlin
- Working Model
- Hybrid, Onsite
- Diversity
- Open for all genders
