Research Scientist Simulation Agents

Advance simulation agents at Waabi in Toronto, San Francisco, Dallas, or Pittsburgh using imitation learning and reinforcement learning.As a Research Scientist on the Behaviors team, you will develop models and algorithms for Waabi World. You will define realistic scenarios, generate training signals, and support the scientific safety case for autonomous transportation. The work spans simulation agents, generative models, planning, search, and foundation models.Key Responsibilities:
Own research agendas for realistic, controllable simulation agentsAdvance imitation and reinforcement learning methodsCollaborate with simulation, autonomy, and safety teamsMentor junior scientists and internsPublish research at top-tier machine learning or robotics conferencesRequirements:
Master’s or PhD in machine learning, computer science, engineering, or related fieldStrong imitation learning or reinforcement learning backgroundPublications in top-tier machine learning or robotics venuesProficiency with PyTorch, TensorFlow, or JAXExperience with self-driving or traffic simulation is a bonusBring research leadership, modern machine learning frameworks, and simulation expertise to Waabi’s autonomous transportation systems.
#J-18808-Ljbffr