Varun Rathore

Applied AI Engineer specializing in Generative AI, Retrieval-Augmented Generation (RAG), LLM APIs (GPT-4, Claude 3.5 Sonnet), and autonomous multi-agent systems. Delivered production FastAPI backends at 2,300+ RPS with 0.46ms latency. Experienced across Python, Docker, AWS/GCP, and the full AI development lifecycle — from prompt engineering and vector database design to CI/CD deployment.

Software Developer Intern - QRACE — National Institute of Technology, Delhi - Delhi

(2025-06 - 2025-10)

• Engineered automated Python benchmarking pipelines to stress-test probabilistic computational models, improving system predictability and edge-case validation across enterprise-grade research deployments.
• Eliminated critical execution bottlenecks via algorithmic redesign, achieving an 85% acceleration in computational convergence speed and directly improving research iteration cycles.
• Built modular Pytest frameworks enabling reproducible benchmarking and regression verification; applied DSA principles to reduce bottleneck time complexity across data processing pipelines.

B.Tech - Computer Science & Engineering - RGPV University (2026-06)