AI Research Engineer, Computer Vision & VLMs

Sourced from emploive.com

Palona AI is seeking an AI Research Engineer to develop visual intelligence for physical world applications, starting with restaurant environments. The role focuses on computer vision and vision-language models (VLMs) to understand people, objects, and activities in real-time despite challenging conditions like occlusion and lighting changes. You will combine research depth with engineering ownership, from dataset creation and model training to production deployment.

• Develop computer vision and VLM approaches for scene understanding, object detection, tracking, and activity recognition.
• Adapt and fine-tune vision-language models for visual grounding, temporal reasoning, and structured prediction.
• Design training strategies including supervised fine-tuning, distillation, and domain adaptation.
• Build representative image/video datasets and rigorous evaluation benchmarks.
• Deploy efficient inference pipelines with monitoring and quality gates.

• 3+ years of research or applied development experience in computer vision or multimodal learning.
• Demonstrated research track record via publications, open-source contributions, or industry projects.
• Strong foundations in deep learning, visual representation learning, and experimental design.