Reinforcement Learning Research Engineer
Develop and evaluate learned policies for sequential decisions under uncertainty, with a focus on robustness and reproducibility.
- Location
- Kyiv / remote
- Experience
- Senior
- Working arrangement
- Arrangement to be discussed
Requirements
- Hands-on experience training and debugging reinforcement learning agents.
- Strong understanding of optimisation, probability and experimental design.
- Ability to implement research ideas in Python and explain when they do not work.
Responsibilities
- Translate a control problem into environments, rewards and measurable baselines.
- Run policy-training experiments with seed sweeps and held-out scenarios.
- Study reward exploitation, distribution shifts and the limits of sim-to-real transfer.
Useful evidence
- A reproducible RL experiment, paper implementation or deployed policy.
- Robotics, offline RL and large-scale rollout infrastructure are useful experience.
Working terms
- Startup culture, a goal-oriented team, and a research mindset
- The opportunity to apply your engineering skills to tools and systems for fellow engineers and help shape the future of AI
- Latest-generation MacBook Pro
- An in-house GPU cluster for training and experimentation
- 20 working days of annual leave
- English courses, educational events, and conferences
- Medical insurance
Tools & systems
PyTorchIsaac LabMuJoCoRayWeights & Biases
Relevant experience matters more than knowing every tool listed.