[Hiring] Research Engineer @ellamind

Role Description

A model only gets good at work it has practiced. Ours practice on thousands of made-up tasks: a caseworker's queue that needs triaging, a spreadsheet that refuses to reconcile, a policy that has to be applied to a document nobody formatted properly, a broken repo in a sandbox.

Somebody has to build those worlds, and then find an honest way to tell whether the model did the job or only looked like it did. We'd like that to be you.

In plenty of places, environment work is treated as plumbing for the "real" researchers. We see it the other way round. Most of what our models can do, they learned from their tasks. So you'd work directly with the people running training, you'd see what your tasks did to the model one run later, and you'd have a say in what the next one learns.

What you'll work on

• Environments for long, multi-step work with tools, documents, and code.
• Generators that turn one good task idea into thousands, hard ones included.
• The checks that decide whether the work got done: tests, state checks, rubric-based judges.
• Catching the model cheating by reading rollouts and closing shortcuts.
• Measuring what a task set really did to the model and deciding which ones to scale and which to drop.
• Helping decide what we publish, including environments, datasets, and benchmarks.

Qualifications

• You've built something that trained or evaluated an LLM, such as an environment, a benchmark, an eval harness, or a data pipeline.
• Your Python is solid and your engineering habits are real.
• You read the data and provide opinions about what's wrong with it.
• You have a feel for what makes a task worth training on: it's realistic, verifiable, and hard to game.
• You write clearly enough that the rest of the team can trust a result without re-running it.
• You live in the EU and are allowed to work here; English is required, German is a bonus.

Requirements

• RL experience (GRPO- or PPO-style training, reward design) is a plus.
• Real knowledge of a field where agents do actual work, like law, finance, insurance, or public administration.
• Sandboxing infrastructure experience (Docker, Firecracker, Kubernetes).
• Open-source contributions are appreciated.
• German language skills are handy, as many tasks start as German-language processes.

Benefits

• Work from anywhere in the EU, ideally Germany.
• Real compute: hundreds of GPUs across EuroHPC and commercial compute.
• Access to AI tools that make your work easier.
• Your name on public work, with the first open-source release planned for Q1 2027.
• Founders you can easily message and a research team worth learning from.
• An office option in Bremen or Berlin.

How to apply

Upload your CV through the form and tell us, in a few lines, about one thing you built that you're proud of. Links to GitHub, papers, a blog post, or a messy notebook are all welcome. Please don't write us a polished cover letter; we'd rather read the notebook.

We're hiring for three RL roles at the same time: environments and data, post-training, and alignment and reward modeling. If you're somewhere between two of them, apply to the closer one and say so. We'll figure it out together.

We care more about what you've built and how you think than about how your CV reads. If you don't tick every box, apply anyway. Hardly anyone does, and different perspectives make our models and our team better.

Company Description

At ellamind, we develop language models and the methods that make them better. Our team trains its own models, builds RL environments, datasets and benchmarks, and researches how to reliably measure and systematically improve the capabilities of LLMs.

• We are known for our leading German-language open-source models.
• We actively share what we learn, including through the open-source community DiscoResearch and as part of the OpenEuroLLM program.
• As a cash-flow-positive startup, we work with well-known partners such as Deutsche Telekom, the German Federal Government, and leading healthcare providers.
• Our headquarters is in Bremen, and we offer competitive pay, equity options, and a short line to the founders.