Senior Machine Learning Engineer, LLM/VLM Visual Reasoning

You will design and implement state-of-the-art models and algorithms for spatial-temporal visual reasoning in autonomous driving contexts, leveraging large language and vision models. You will develop and maintain training and evaluation pipelines for VLM models, focusing on decision-making rationale and free-form QA metrics. You will collaborate with ML engineers and researchers to integrate visual reasoning capabilities into production systems. You will lead efforts to curate large-scale rationale/QA data and establish rigorous evaluation metrics. You will explore advanced techniques, including supervised fine-tuning (SFT) and reinforcement learning (RL), to optimize performance on complex visual reasoning tasks. You will analyze and interpret large-scale sensor data to identify challenges and opportunities to improve LLM/VLM performance in real-world driving environments.