Czym bedziesz sie zajmowac?About the company:US-based AI startup focused on building the next generation of training data for LLMs.The team partners with top AI labs to create realistic RL environments where models encounter research and engineering challenges, iterate, and learn from feedback, pushing AI closer to its full potential.Project:Design and build reinforcement learning environments to teach LLMs advanced reasoning and modern ML concepts.Candidates will work on realistic feedback loops where models encounter research and engineering problems and iterate on solutions.What you will do:Build and maintain RL/ML environments for LLM trainingImplement robust, production-quality Python code (not just notebooks)Deploy and run environments in Docker with focus on reliability and iteration speedAnalyze model performance and respond to feedback efficientlyCollaborate with research teams to translate papers and ideas into RL problemsKogo poszukujemy?Client:US startupRecruitment process:2 meetings with hiring managers, followed by a phone screen with our recruiter and technical testFully remote workSkills:Strong Python (engineering-quality)Docker and production mindsetUnderstanding of LLMs and their limitationsAbility to meet throughput expectationsAdvanced English (C1/C2) and >=4 hours overlap with US time zonesNice-to-have:Deep knowledge of transformer internals and LLM training/inferenceExperience with inference libraries (vLLM, SGLang, etc.)CUDA or Pallas kernel development experiencePublications or open-source contributions in active DL/ML researchExperience building interactive RL environments and RL-based learning systemsWhat#39;s in it for you?Fully remote, flexible work schedule with some overlap to US time zoneDirect impact on how LLMs learnCollaboration with top AI researchers and labsExposure to cutting-edge RL and ML projectsCzego wymagamy?5 lat doswiadczenia na podobnym stanowiskuZnajomosci:PythonDockerLLMMLMile widziane:Reinforcement LearningAIJezyki:AngielskiJakie warunki i benefity otrzymasz?35000-74000 PLN miesiecznieB2B - Praca projektowa (100%)Praca zdalna:W calosciKim jestesmy?Work for the largest bank in Europe, which operates in more than 65 countries around the world giving us access to over 90% of all world trade flows.Don't hesitate to apply, create future of banking with us!Who we are? Verita HR is an international company providing recruitment support within #Fintech, #Finance and #Banking market in EMEA.We connect the most innovative organizations with the best people in the market.We conduct systematic market research, which allows our Digital Teams to be a step ahead of the competition.. Experience: 3 years required