Anvesha Mittal

Anvesha Mittal

—CSE@BIT MESRA’27 || Amazon ML Summer School 2025|| DSA || Python || C++ || BVB’23

Jaipur, IndiaArtificial Intelligence and Machine Learning
4roles
31skills
4education

About

B.Tech Computer Science student with a CGPA of 8.59 and experience building production-ready RAG systems and high-throughput data processing engines during AI/ML internships.

Experience

AI/ML Intern

Bootcoding Pvt. Ltd.

3 mos

Generated structured interview transcripts in JSON/JSONL schemas; collected, cleaned, and normalized job description data; built an API-based document ingestion pipeline; implemented semantic search using Qdrant, embeddings, chunking, and named vectors; engineered a high-throughput system handling 150–200 concurrent inputs and processing 7,600+ documents.

Amazon ML Summer School

Amazon

1 mo

Student Volunteer

Vibrations - BIT Mesra, Jaipur Campus

2 yrs

AI/ML Intern

Shoro AI Labs

Dec 2025 - Feb 2026

Engineered a two-phase LLM formatting pipeline and multi-pass Markdown normalization engine; designed comparison question-to-JSON-to-table rendering using SSE; developed automatic subject routing with LLM intent detection and vector similarity scoring; contributed to a production codebase using Git, source branches, and reviewed pull requests.

Education

Birla Institute of Technology, Mesra

Bachelor of Technology - BTech, Computer Science

[object Object]

Bharatiya Vidya Bhavan's

[object Object]

Birla Institute of Technology, Mesra

Bachelor in Computer Science Engineering, Computer Science Engineering

2023 - 2027

CGPA: 8.59

Bhartiya Vidya Bhavan Vidyashram, Jaipur

2012 - 2023

Class 10th: 91%; Class 12th: 84.6%

Skills

C++CPythonData Structures & AlgorithmsObject-Oriented ProgrammingOperating SystemsDBMSRAGVector DatabasesEmbeddingsRegressionClassificationClusteringNeural NetworksFastAPILangChainTensorFlowScikit-learnDockerGitAzure OpenAIFAISSGit WorkflowsPull RequestsCode ReviewsLangGraphQdrantSSEPandasNumPyPyTorch

Projects

Opportunity Radar AI

AI-native stock analysis platform for Indian retail investors using a five-agent LangGraph pipeline comprising Researcher, Bull, Bear, Judge, and Alert agents. Includes a Divergence Detector cross-referencing FII/DII institutional flows with retail social sentiment to flag high-risk trap signals.

RAG System

Production RAG chatbot built with FastAPI and Azure, enabling real-time knowledge base updates through asynchronous ingestion. Reduced query latency by 30–40% through FAISS index tuning and async I/O.

Smart Product Price Prediction

End-to-end ML pipeline for 75,000+ listings using regex-based feature extraction. Trained a TF-IDF and Ridge model with GridSearchCV and SMAPE, achieving a 40.16 validation score.