Vaishnavi

Interim Engineering Intern – SW

Delhi, IndiaTechnology
2roles
29skills
1education

About

Vaishnavi Nandkishor Bisen is a dedicated Electrical Engineering student at IIT Delhi with a strong foundation in software development and automation. With hands-on experience in engineering internships at Qualcomm and Lovely Pets LLP, she has demonstrated her ability to innovate and optimize processes, significantly enhancing productivity and efficiency.

Experience

Interim Engineering Intern – SW

Qualcomm

May 2025 - Jul 2025 (2 mo) · Noida

Developed a modular TCL automation framework that detected and auto-fixed design violations, reducing manual fix time by 40% and enabling engineers to resolve issues 2.5 times faster. Engineered an LLM-powered query engine for natural-language analysis of design reports, streamlining processes for over 50 design engineers.

Software Development Engineer Intern

Lovely Pets LLP

May 2024 - Jul 2024 (2 mo)

Created a React Native CRM frontend for over 20,000 customer profiles across 8 store locations, enhancing operational analytics for 50+ staff. Optimized MySQL schema design, achieving a 50% reduction in query latency and a 20% decrease in storage footprint.

Education

Indian Institute of Technology Delhi

B.Tech, Electrical Engineering

2022 - 2026

GPA: 7.61/10.0

Skills

C++PythonJavaSQLTCLHTMLCSSData Structure & AlgorithmMachine LearningNumPyPandasMatplotlibSeabornScikit-learnXGBoostGitLinux/UnixStreamlitData Structures and AlgorithmsReact NativeMySQLQLoRAmPLUG-Owl2REST APIGradioLambdaMARTXGBoostRankerRabin-Karp algorithmAVL trees

Projects

Visual Question Answering using LLMs

Developed a chart QA system using mPLUG-Owl2 with a 2-stage QLoRA pipeline on over 600K examples, improving accuracy by 18% and reducing hallucinations by 25%. Deployed a production-grade system with REST API backend and Gradio UI for real-time and batch inference.

Personalized Offer Ranking

Created an end-to-end learning-to-rank system using LambdaMART and XGBoostRanker, processing over 500K daily transactions for 10K+ users, improving recommendation relevance by 32% and doubling offer-to-conversion rates.

Advanced Search Engine and Corpus Q&A Tool

Built a search engine using the Rabin-Karp algorithm to find substring patterns across 100K+ documents with sub-100ms query latency, achieving 85% precision and reducing LLM hallucination by 30%.

E++ Expression Evaluator and Compiler

Implemented a custom data type for arbitrary-precision integers and built a compiler converting expressions to stack-machine bytecode, achieving a 40% runtime improvement and 25% memory reduction across 500+ test cases.

Volunteering

Coordinator

Rendezvous

2025

Coordinator

Tryst

2024

Class Representative

HWC

2023