About this role
Senior Researcher in multi-modality to shape next-generation multimodal foundation models and agentic AI for gaming, focusing on multimodal understanding, post-training (SFT, RLHF/RLAIF), reasoning, grounding, and agent planning. Responsible for designing and executing end-to-end experiments, collaborating to deploy research prototypes at scale, and publishing at top-tier conferences.
Skills for this role
Multimodal understandingVision-language reasoningPre-training of LLMsPost-training of LLMsVision-Language Models (VLMs)Multimodal Large Models (MLLMs)Reinforcement learningLLM-based agentsRepresentation learningSupervised Fine-Tuning (SFT)Reinforcement Learning from Human Feedback (RLHF)Reinforcement Learning from AI Feedback (RLAIF)Reward modelingPreference alignmentExperiment designData benchmarkingModel trainingModel evaluationPyTorchJAXAgent planningGroundingImage understandingVideo understandingAudio understandingPublishing research