and experience in building single/multi-agent systems based compact LLMs finetuned with Agentic RL for reasoning/planning, tool-use.... *Strong hands-on experience with Large Language Models and related technologies (i.e. training-time scaling with Agentic RL, Prompt...
and deploying novel algorithms and training frameworks. You will design and develop RL infrastructure and reward modeling strategies..., including online RL settings, with demonstrated impact on domain-specific decision-making and measurable improvements in policy...
techniques and theory (e.g. graph NN, RL) Experience with CAD optimization algorithms Where you will be working Cork...