Computer Vision Vlm Research Engineer

Shape visual intelligence for Palona’s restaurant AI through computer vision and vision-language models, connecting images and video to useful 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 approachesAdapt and evaluate vision-language models for temporal reasoningBuild datasets, annotation workflows, and difficult evaluation setsDesign experiments measuring robustness, latency, cost, and hallucinationsDiagnose failures from occlusion, lighting, and domain shiftRequirements:
Three-plus years in computer vision or multimodal learningResearch track record through publications, projects, or industry deliveryStrong deep learning, Python, PyTorch, and experimental design foundationsExperience training, fine-tuning, or evaluating VLMsGraduate research degree or equivalent research experienceApply computer vision, VLMs, and rigorous experimentation to build reliable visual intelligence for Palona’s restaurant products.
#J-18808-Ljbffr