A company is looking for a Research Engineer focused on reinforcement learning.Key ResponsibilitiesBuild training infrastructure and reward pipelines from scratchFine-tune models to achieve state-of-the-art results in web data extractionBridge LLM agents and classical RL techniques to improve agent workflowsRequired Qualifications3+ years of experience in applied reinforcement learning or ML engineeringProven ability to build training infrastructure and reward models independentlyExperience in fine-tuning models to achieve best-in-class performanceFluency in both classical RL methods and modern LLM techniquesExperience deploying models in production environments