Design and build MLE/SWE environments and diverse tasks.
Target a specified language model and satisfy the required difficulty distribution.
Requirements
Experience with PyTorch or JAX at the framework level (not just importing a model)
Familiarity with RL concepts: reward functions, environment design, training loops, evaluation
Ability to read ML papers and implement them. This is a core part of the job. If someone hasn't reproduced or extended a research result, they'll struggle here.
Production Python skills: Docker, git, clean code, reproducible environments. Notebooks-only people won't work.
Exposure to any of: model training/finetuning, inference optimization, CUDA/Triton kernels, distributed training, model internals (attention, KV caches, tokenizers)
Tech Stack
Docker
Python
PyTorch
Benefits
100% remote work (but we have offices in Krakow and Warsaw and we’re happy to meet there from time to time 😉)
300 PLN to use on our benefits platform, Worksmile
gift cards, medical services, sports, etc.
Our B2B contract contains provisions that allow you to obtain IP BOX support
Integration events, education opportunities and much more…
A unique opportunity to take your career to the next level
we’re looking for people who want to create an impact. You have ideas, we want to hear them!