Vision Language Model Engineer

EchoTwin AI is pioneering AI-driven infrastructure intelligence, transforming cities into resilient digital twins. They are seeking a Vision Language Model Engineer to design, develop, and optimize advanced vision-language models for applications like image captioning and visual question answering. The role involves collaborating with cross-functional teams and contributing to the data pipeline.

Requirements

• Design and implement state-of-the-art vision-language models.
• Develop and fine-tune models for image captioning, visual question answering, and text-to-image generation.
• Collaborate with data scientists and software engineers.
• Optimize model performance for accuracy, latency, and scalability.
• Conduct experiments and iterate on architectures.
• Stay up-to-date with the latest research in vision-language models.

Benefits

• Medical, dental, and vision coverage
• Flexible Spending Account (FSA)
• Dependent Care Flexible Spending Account (DCFSA)
• 401(k) with company matching
• Profit sharing