Computer Vision Practitioner for AI Model Evaluation

Join a cutting-edge GenAI team at a leading AI lab, where your expertise will be pivotal in developing advanced AI models. This role focuses on building and evaluating frontier models, requiring experienced computer vision practitioners to serve as ground-truth experts. Overview

As a Computer Vision Expert, you will design robust computer vision problems, such as detection, segmentation, recognition, vision-language and multimodal reasoning, or generation. You will create executable tests, analyze model outputs, and identify reasoning and capability gaps in target models. This part-time W-2 employment position offers the flexibility of fully remote work within the United States, with an expected commitment of approximately 20 hours per week.

• Task design and development: Create challenging, real-world computer vision problems that target specific capability gaps in frontier AI models.
• Spec and golden-solution generation: Integrate problems into an agentic development environment, preparing all necessary components using Python.
• Evaluation and analysis: Assess the performance of target models on your tasks.
• Headroom identification: Identify and classify tasks where the target model fails.
• Collaborate with other experts: Work with fellow subject-matter experts to ensure evaluations are consistent and accurate.

• Deep, hands-on experience in computer vision, gained through applied industry work, research, or a graduate/PhD background.
• Working proficiency in Python, applied in research, industry, or open-source projects.
• Strong command of modern computer vision methods, including deep learning architectures and standard tools (e.g., PyTorch/TensorFlow).
• Ability to commit to approximately 20 hours per week.
• Preferred experience in AI training, model evaluation, or data annotation.
• Excellent written communication skills and the ability to work independently while managing your own time.

This position is part-time, with an expected workload of around 20 hours per week. The role is fully remote, allowing for flexibility in your work schedule.

Hourly compensation ranges from $80 to $110.

This role is open to candidates located in the United States.