&

We are looking for experienced AI/LLM Evaluation Specialists to join our AI Human Judgment Operations team and work on high-complexity evaluation and alignment projects for advanced AI models.

: WFO
: 3-Month Contract

:
• Evaluate and rank AI/LLM responses for factuality, helpfulness, safety, reasoning, and instruction-following
• Perform side-by-side and multi-turn evaluations
• Identify model errors, hallucinations, and reasoning failures
• Rewrite and improve sub-optimal AI responses
• Evaluate complex reasoning and AI agent/tool-use workflows
• Support calibration, QA, and evaluation guideline updates

' :
• 2+ years of hands-on experience in AI/LLM evaluation, RLHF, AI model evaluation, or complex AI annotation
• Strong analytical and critical-thinking skills
• Excellent written English (C1 or above) with the ability to provide transparent evaluation rationales
• Experience with complex rubrics and rapidly changing guidelines
• AI/LLM, Generative AI, or AI data platform experience preferred
• Python/prompt engineering knowledge is an added advantage

📌 Senior AI Evaluation & RLHF Specialist (Noida)
🏢 Innodata India
📍 Noida