Shape visual intelligence for Palona’s restaurant AI through computer vision and vision-language models, connecting images and video to helpful actions. As an AI Research Engineer, you will study image and video understanding, spatiotemporal reasoning, and multimodal models. You will formulate research questions, build datasets, train models, and evaluate results. Your work will connect research with product and engineering systems for real restaurant environments. Key Responsibilities:

Develop scene understanding, detection, tracking, and activity recognition approaches Adapt and evaluate vision-language models for temporal reasoning Build datasets, annotation workflows, and difficult evaluation sets Design experiments measuring robustness, latency, cost,



and hallucinations Diagnose failures from occlusion, lighting, and domain shift Requirements:

Three-plus years in computer vision or multimodal learning Research track record through publications, projects, or industry delivery Strong deep learning, Python, PyTorch, and experimental design foundations Experience training, fine-tuning, or evaluating VLMs Graduate research degree or equivalent research experience Apply computer vision, VLMs, and rigorous experimentation to build reliable visual intelligence for Palona’s restaurant products.

📌 Computer Vision VLM Research Engineer (Toronto)
🏢 Palona AI
📍 Toronto