ML - Data Scientist

What you'll do

• Design and maintain representative evaluation sets and golden sets; analyze coverage and data distributions.
• Run human annotation programs and develop automated metrics and LLM-as-judge systems, calibrating them against human labels.
• Analyze and communicate model comparisons, statistical findings, root causes, and prioritized recommendations to partner teams.

What they ask for

• MS degree and minimum 5 years of relevant industry experience.
• 5+ years in data science, machine learning evaluation, algorithm analysis, or related technical disciplines.
• Experience designing and analyzing ML or generative-model evaluations and experiments, including sampling design, significance testing, and confidence intervals.
• Strong Python skills and comfort with SQL; familiarity with AI-assisted analysis workflows, foundation models, agentic systems, or intelligent automation.

Nice to have

• Experience with 3D Gaussian splats, diffusion models, or perceptual quality; or building and validating LLM or VLM judges against human ratings.
• Experience building web-based labeling or review tools.

Pay

USD $184,700 to $324,800 base pay

Tools

Python, SQL, LLM, VLM, 3D Gaussian splats

AI focus

Evaluates generative image and video features; develops automated metrics and LLM-as-judge systems, calibrates them against human labels, and uses AI-assisted analysis workflows.