Open to opportunities

Chirag singh

@chiragsingh

Message

I evaluate and improve LLM outputs through prompt engineering, AI quality workflows, and rigorous human feedback.

India

Message

What I'm looking for

I’m looking for an AI/LLM evaluation or AI quality role where I can improve model outputs through prompt engineering, rigorous evaluation, data validation, and human feedback workflows.

At Innodata, I evaluated 60–70 LLM responses daily, achieving a 2.90 quality score against a 2.00 benchmark. I assess outputs for accuracy, relevance, consistency, hallucinations, formatting, and adherence to evaluation criteria.

I design and optimize prompts to test model behavior, improve response quality, and support AI data annotation, validation, and QA workflows. I’ve also mentored junior analysts on evaluation standards and prompt review methods.

Before AI/LLM work, I delivered market intelligence reports at Arizton Advisory & Intelligence, analyzing industry trends, competitive landscapes, and consumer behavior. I bring experience turning large datasets and client requirements into structured, evidence-based recommendations.

Experience

Work history, roles, and key accomplishments

Analyst – AI/LLM

Innodata India Pvt. Ltd.

Nov 2025 - Jul 2026 (8 months)

Evaluated 60–70 LLM responses per day, achieving a 2.90 quality score against a 2.00 benchmark. Designed and optimized prompts to test model behavior, detect hallucinations, and improve response quality.

LLM Evaluation Prompt Engineering Data Annotation Quality Assurance Hallucination Detection AI Quality Analysis

Associate Analyst – Market Research

Arizton Advisory & Intelligence

Jul 2023 - Aug 2025 (2 years 1 month)

Delivered ~12 in-depth market intelligence reports per quarter, analyzing industry trends and competitive landscapes. Designed research frameworks and synthesized large datasets into actionable recommendations.

Market Research Competitive Intelligence Data Synthesis Excel Segmentation Consumer Analysis