# Kriti Verma

AI Test Analyst | 2 years experience | Indore, Madhya Pradesh

Sample resume with fictional details. Replace the content with your own experience and qualifications.

Email: [Your email] | Phone: [Your phone]
LinkedIn: [Your LinkedIn URL] | GitHub / Portfolio: [Your portfolio URL]

## Professional Summary

- Emerging AI Test Analyst with 2 years of experience in validating AI/ML models and ensuring data quality
- Proficient in data validation techniques and statistical analysis for training datasets
- Skilled in performing model explainability checks and bias detection in AI systems
- Experienced in using Python and pandas for data preprocessing and analysis
- Knowledgeable in machine learning concepts and evaluation metrics for model performance
- Familiar with data profiling tools and techniques for identifying data anomalies
- Collaborative professional working with ML engineers to ensure reproducible experiments
- Strong analytical skills for designing test cases that cover edge cases in AI models

## Technical Skills

Python, Pandas, NumPy, Scikit-learn, Data Validation, Model Explainability, Bias Detection, Statistical Analysis, Jupyter Notebook, Git, SQL, Machine Learning Basics, Data Profiling Tools, DeepEval, RAGAS, PromptBench, LangSmith (Basic), Hallucination Testing, RAG Pipeline Testing, OWASP LLM Top 10, AI Safety Testing, Agentic Workflow Testing (Basic)

## Work Experience

### AI Test Analyst

[Company name] | [Start date - End date]

2 years of experience as an AI Test Analyst at a growing AI startup in Indore. Focused on testing AI-powered applications, ensuring data quality, and validating model outputs for accuracy and fairness.

### Responsibilities

- Validate training and validation datasets for quality, completeness, and representativeness
- Perform model explainability checks and interpretability analysis
- Design and execute test cases for bias detection and fairness evaluation
- Collaborate with ML engineers to ensure reproducible model training and testing
- Analyze model performance metrics and provide recommendations for improvement
- Document testing procedures and results for regulatory compliance
- Stay updated with latest AI testing methodologies and ethical guidelines
- Participate in cross-functional teams to integrate testing into AI development lifecycle
- Apply 2026 LLM testing practices: hallucination testing (DeepEval), RAG pipeline evaluation (RAGAS), adversarial prompt testing (PromptBench), and OWASP LLM Top 10 compliance validation

## Project Experience

### NLP Classifier Validation

Conducted comprehensive dataset profiling and bias testing for a natural language processing classifier, identifying and mitigating gender bias in training data, resulting in 15% improvement in model fairness. Technologies: Python, Pandas, Scikit-learn, Data Profiling Tools.

### Image Recognition Model Testing

Performed data validation and explainability checks for an image recognition model, creating test cases for edge cases and adversarial inputs, ensuring robust performance across diverse datasets. Technologies: Python, NumPy, Jupyter Notebook, Statistical Analysis.

### Recommendation System Evaluation

Validated training datasets and model outputs for a recommendation engine, implementing bias detection algorithms and collaborating with ML team for reproducibility, leading to more accurate user recommendations. Technologies: Pandas, Scikit-learn, SQL, Git.

### LLM Hallucination and RAG Validation

Designed test suites for a RAG-based FAQ chatbot using RAGAS to evaluate context precision, faithfulness, and answer relevancy scores. Applied DeepEval hallucination detection and PromptBench adversarial scenarios to identify prompt injection vulnerabilities. Aligned test approach with OWASP LLM Top 10. Technologies: RAGAS, DeepEval, PromptBench, Python, OWASP LLM Top 10, Hallucination Testing, RAG Pipeline Testing.

## Education

B.Tech in Computer Science from Indian Institute of Technology Indore, Indore (2019-2023, 8.7 CGPA)

## Certifications

Certified AI Ethics Specialist (In Progress), Python for Data Science Certification

## Achievements

Awarded "AI Ethics Champion" for contributions to bias detection in 2024; Published a paper on dataset validation techniques; Active member of AI testing community forums