Lavanya D

AI Engineer with hands-on experience in Large Language Model (LLM) evaluation, Generative AI, Prompt Engineering, and Machine Learning. Worked as an Analyst – AI/LLM Practice at Innodata, contributing to AI response evaluation, prompt validation, and annotation workflows. Proficient in Python, TensorFlow, Flask, REST APIs, Knowledge Graphs, and Natural Language Processing.

Passionate about building scalable AI applications and continuously learning modern AI technologies including RAG, AI Agents, and AI Inference.

Analyst – AI/LLM Practice - Innodata India Pvt. Ltd.

(2026-04 - 2026-07)

• AI Response Evaluation: Evaluated AI-generated responses for factual accuracy, contextual relevance, linguistic quality, and policy compliance across diverse domains.
• Prompt Validation: Performed prompt evaluation, response validation, and annotation following project-specific Large Language Model (LLM) quality guidelines.
• Quality Improvement: Identified inconsistencies, documented feedback, and contributed to improving response quality for production-grade AI systems.
• Collaboration: Worked closely with QA teams to maintain annotation consistency and high-quality datasets for AI model evaluation.

Bachelor of Technology (B.Tech) - Artificial Intelligence & Machine Learning - Dayananda Sagar University (2021 - 2026)