B Lavanya Devi

I am an experienced analyst with 1 year, 9 months of work on AI evaluation and data annotation projects for Google. I have worked on creating and testing prompts, checking AI answers for accuracy, and tagging data for education, Android, and gaming tasks. I am skilled in evaluating AI responses, following task guidelines, and maintaining high quality. I have good communication skills, work well in a team, and always complete tasks on time. I’m looking for a role where I can learn more, and grow in my career.

• Prompt Engineering – Creating and optimizing structured prompts for LLMs (Google AI Studio)
• LLM evaluation – assessing model outputs for accuracy, coherence, reasoning, and relevance
• Human evaluation (HumanEval) – scoring AI responses based on quality, logic, and completeness
• Rubric-Based Scoring – Using structured rubrics to consistently evaluate AI-generated content.
• Android QA testing – validating voice assistant responses, app behaviors, and intent mapping
• Data annotation – tagging educational, mobile, and gaming data for AI training and analysis
• Analytical Thinking – Identifying hallucinations, logical gaps, and inconsistencies in AI output.
• Attention to detail – maintaining high annotation and evaluation accuracy across tasks
• Documentation and reporting – logging errors, trends, and improvement suggestions for model refinement

• Telugu
• English
• Hindi