RL Environments Research Engineer

Hello World!

We are The Codest - International Tech Software Company with tech hubs in Poland delivering global IT solutions and projects. Our core values lie in Customers and People First approach that prioritises the needs of our customers and a collaborative environment for our employees enabling us to deliver exceptional products and services.

Our expertise centers on web development cloud engineering DevOps and quality. After many years of developing our own product - Yieldbird which was honored as a laureate of the prestigious Top25 Deloitte awards we arrived at our mission: to help tech companies build impactful product and scale their IT teams through boosting IT delivery performance. Through our extensive experience with product development challenges we have become experts in building digital products and scaling IT teams.

But our journey does not end here - we want to continue our growth. If youre goal-driven and looking for new opportunities join our team! What awaits you is an enriching and collaborative environment that fosters your growth at every step.

We are currently looking for a RL Environments Research Engineers.

Our client builds reinforcement learning environments and training tasks for frontier AI labs. The work is technical research-adjacent and hands-on. Were not looking for web developers or backend engineers who have used LLM APIs.

Key Responsibilities:

• Design and build MLE/SWE environments and diverse tasks.

• Target a specified language model and satisfy the required difficulty distribution.

The right candidates have:

• 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 hasnt reproduced or extended a research result theyll struggle here.

• Production Python skills: Docker git clean code reproducible environments. Notebooks-only people wont work.

• Exposure to any of: model training/finetuning inference optimization CUDA/Triton kernels distributed training model internals (attention KV caches tokenizers)

  Nice to have but not required:

• Publications or competitive programming background

• Experience with MuJoCo game environments or simulation frameworks

• Scientific computing (Rust C numerical methods)

Profiles that dont fit:

• Web/backend engineers whose AI experience is limited to calling LLM APIs building RAG pipelines or prompt engineering

• Data engineers or data scientists who work in notebooks and dashboards

• DevOps/infra engineers without ML depth

The simplest test: have you ever trained a model from scratch or built something where a model learns from an environment

Our Promise (what you can expect from us):

• 34 - 44k PLN (B2B/useme)

• 100% remote work (but we have offices in Krakow and Warsaw and were 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 - were looking for people who want to create an impact. You have ideas we want to hear them!

Questions insights Feel free to reach out to our recruiting team:

In the meantime feel free to visit our website where you can find key facts about us.