About the Role

We're seeking a visionary AI Research Engineer to help us push the boundaries of natural language to vector graphic conversion. You'll work on cutting-edge multimodal models that translate creative descriptions into precisely structured XML formats.

You'll Build

• • Next-generation art-to-XML conversion models with 90%+ accuracy
• • Advanced shape recognition systems for complex vector operations
• • Real-time animation synthesis from motion descriptions
• • Cross-modal embeddings linking text descriptions to geometric patterns

What We Expect

• • 3+ years in deep learning with PyTorch/TensorFlow
• • Expertise in vision-language models (CLIP, BLIP, etc)
• • Experience with SVG/XAML structure and validation
• • PhD or equivalent in AI, Machine Learning, or related field

We Offer

• • Flexible work schedule with full remote option
• • $25,00 annual learning budget for conferences/courses
• • 30% time dedicated to personal research projects
• • Collaborative team with weekly innovation sprints