Looking for a job

Raghava Donga

@raghavadonga

AI QA Engineer at Turing evaluating LLM reasoning and reliability; I’ve also built RAG platforms and agentic AI workflows.

India

Message

At Turing, I evaluate and benchmark large language model outputs across coding, reasoning, and technical domains. I design edge-case tests and validation prompts, and help curate supervised datasets to improve model fine-tuning accuracy.

I built Aegis AI, a multi-service RAG security platform using MongoDB Atlas Vector Search and real-time WebSocket telemetry. At Harvin Technologies, I integrated LLMs with web platforms using the Gemini API and developed prompt-chaining pipelines that increased retrieval accuracy and response relevance by 40%.

Experience

Work history, roles, and key accomplishments

Current

AI QA / Engineer

Current

Turing

Evaluate and benchmark Large Language Model outputs across complex coding, reasoning, and technical domains to ensure model alignment and response reliability. Design rigorous test scenarios, edge-case evaluations, and automated validation prompts to minimize hallucinations and bias.

Model Evaluation Benchmarking LLM Prompt Engineering Test Engineer Data Curation Collaboration

Full Stack Development Intern

Cognifyz Technologies

Nov 2025 - Feb 2026 (3 months)

Engineered responsive React.js UI components and integrated secure RESTful endpoints using Node.js and Express.js. Optimized full-stack feature deployment pipelines, emphasizing code maintainability and cross-browser performance.

React NodeJS ExpressJS REST APIs Deployment Code Maintainability

Generative AI Intern

Harvin Technologies

Jun 2025 - Dec 2025 (6 months)

Integrated LLMs with client-facing web platforms utilizing the Gemini API. Engineered prompt chaining pipelines, increasing AI retrieval accuracy and response relevance by 40%.

Gemini API Prompt Chaining LLM Integrations Automation Content Generation