Data Scientist

You’ll work on complex evaluation challenges across vision, language, and reasoning, developing metrics, datasets, and experimental approaches that help assess the quality and capabilities of next-generation AI models. You will be part of a small international R&D team, contributing to the evaluation of advanced AI systems and exploring new approaches to measuring their performance.

Key Responsibilities

• Design and validate robust evaluation metrics and ground-truth datasets for advanced AI systems
• Assess model accuracy, false positives and false negatives, and overall evaluation quality
• Refine metric normalization and scoring methodologies to ensure consistent and meaningful evaluation
• Develop LLM-based evaluation approaches and methodologies for incorporating human feedback
• Explore and define new evaluation dimensions, including complexity, prompt adherence, and other emerging measures of AI performance

Requirements

• 5+ years of professional experience in Data Science, AI, Machine Learning, or a related field
• Strong data science, analytical, and experimentation skills
• Hands-on experience with AI/LLM evaluation and performance analysis
• Experience designing evaluation metrics, scoring methodologies, and ground-truth datasets
• Understanding of agentic AI workflows and multi-step AI systems
• Experience with 3D, geometry, or rendering is considered a plus

Share this job:

relocation package

competitive compensation packages

performance bonuses

flexible working hours

job rotation

learning through Arnia Academy

attractive projects

trainings

international work experience

referral program

medical benefits