Remote Multimodal GenAI Evaluation Analyst

iMerit Technology; Polska; Remote; PLN 70,000 - 100,000; Full time

Job summary

A technology evaluation firm in Poland is looking for Multimodal GenAI Evaluation Analysts. In this role, you will conduct nuanced evaluations of AI outputs across text, image, and video modalities, ensuring alignment with project standards. Candidates should have at least 1 year of experience in related fields and possess strong analytical skills. Join us to help shape AI systems that are accurate and culturally aware.

Benefits

Competitive compensation

Flexible remote working arrangements

Continuous learning and growth opportunities

Qualifications

• 1+ years of experience in data annotation, LLM evaluation, or related AI/ML domains.
• Demonstrated experience with data annotation tools and software.
• Strong understanding of language and multimodal communication.

Responsibilities

• Evaluate outputs generated by LLMs across text, image, and video modalities.
• Assess quality against project-specific criteria.
• Identify subtle errors and biases in AI responses.
• Provide detailed feedback and scoring of outputs.
• Collaborate with Project Managers and Quality Leads.

Skills

Detail-oriented

Analytical skills

Critical reading

Observational skills

Evaluative skills

Excellent English comprehension (CEFR B2)

Understanding of cultural nuances

Tools

Data annotation tools

Evaluation software platforms

Job description

A technology evaluation firm in Poland is looking for Multimodal GenAI Evaluation Analysts. In this role, you will conduct nuanced evaluations of AI outputs across text, image, and video modalities, ensuring alignment with project standards. Candidates should have at least 1 year of experience in related fields and possess strong analytical skills. Join us to help shape AI systems that are accurate and culturally aware.