Computer Vision Specialist for AI Model Evaluation

Join a leading AI lab''s cutting-edge GenAI team to be at the core of the AI revolution, where your expertise fuels the development of the most advanced AI models. Overview

A leading AI lab is building and evaluating frontier models and needs experienced computer vision practitioners to act as ground-truth experts. You will author challenging, real-world vision tasks, generate reference solutions, and evaluate model outputs to surface reasoning and capability gaps in a target model.

The work centers on designing robust computer vision problems (e.g., detection, segmentation, recognition, vision-language and multimodal reasoning, or generation), building them out with executable tests where applicable, and then analyzing how models and agents behave against them. All applicants are expected to have working proficiency in Python.

This is a part-time W-2 employment position with Cincinnatus LLC, with the opportunity to be placed at a leading AI lab as part of their extended workforce. This role is fully remote within the United States, at approximately 20 hours per week.

• Task design and development: Design challenging, real-world computer vision problems drawn from your area of expertise (e.g., object detection, segmentation, recognition, multimodal/vision-language reasoning, or image/video generation) that target specific capability gaps in a frontier AI model.
• Spec and golden-solution generation: Integrate the problems into an agentic development environment, preparing all necessary components using Python.
• Evaluation and analysis: Evaluate the target model''s performance on your tasks.
• Headroom identification: Identify tasks where the target model fails, and classify the nature of the failure.
• Collaborate with other experts: Work alongside fellow subject-matter experts to keep evaluations consistent and accurate.

• Deep, hands-on experience in computer vision, from applied industry work, research, or a graduate/PhD background in the field.
• Working proficiency in Python, applied in research, industry, or open-source work (not theoretical familiarity).
• Strong command of modern computer vision methods, including deep learning architectures, evaluation, and standard tooling (e.g., PyTorch/TensorFlow).
• Ability to engage reliably for approximately 20 hours per week.
• Past experience in AI training, model evaluation, or data annotation is preferred.
• Strong written communication and the ability to work independently and manage your own time.

This is a part-time W-2 employment position, fully remote within the United States, with an expected commitment of approximately 20 hours per week.

The hourly compensation for this role ranges from $80 to $110.

Applicants must be legally eligible to work in the United States.