AI Quality Evaluation Specialist

Are you a linguistic expert with a passion for cutting-edge AI and data science?

Join a world-leading audio streaming and media service on a high-impact 6-month contract focused on defining the next generation of multilingual AI quality.

This remote role is ideal for a specialist who bridges linguistic nuance with machine learning evaluation methods.

You Will:

• Design & Implement: Create advanced multilingual evaluation frameworks and scoring rubrics (e.g., based on MQM, COMET).
• Calibrate AI: Validate and fine-tune AI evaluation tools (like QUAIL/MetricX) against human gold standards.
• Collaborate: Partner with ML Engineers to build and test linguistic data pipelines and synthetic data generation.
• Ensure Global Quality: Analyze model outputs across locales to guarantee accuracy, fluency, and cultural fit for millions of global users.

Required Experience:

• Expertise in LLM Evaluation or Machine Translation evaluation in multilingual settings.
• Hands-on experience with quality frameworks like MQM, COMET, or designing multidimensional rubrics.
• Background in Applied Linguistics, Computational Linguistics, or Language Quality Research.

Shape the evaluation intelligence layer that underpins a world-class AI ecosystem.

If you find this interesting, please apply here or share your CV to sai saranya. gummadi@ randstad digital .com

Randstad Technologies is acting as an Employment Business in relation to this vacancy.