Akshit Maheshwari

|

an AI/ML developer who likes practical systems, polished interfaces, and work that feels clean, useful, and intentional.

Enthusiast • Builder • Research-minded

Akshit Maheshwari

About me

A motivated undergraduate in IT and Data Science with hands-on experience in AI/ML projects. I focus on making systems measurable and solvable, not just functional - from data preparation and embedding pipelines to ranking logic and retrieval evaluation.

Academic foundation.

Academic track

University School of Information, Communication and Technology

Delhi, IndiaB.Tech - Information and Technology

September 2023 - August 2027

Academic track

IIT Madras

RemoteB.Sc. - Data Science and its Applications

September 2023 - July 2027

Tools and technologies I use.

Languages

CC++PythonJavaScriptSQL

ML / DL

PandasNumPyMatplotlibSeabornImbalanced-learnScikit-learnTensorFlowOpenCVPyTorchHugging FaceTransformersGANs

Frameworks

FlaskFastAPILangChainLangGraphReact

Databases

MySQLPostgreSQLMongoDBVector StoresNeo4j

Tools

MLflowDockerDagshubGitJupyter Notebooks

Cloud

AWS S3AWS ECR

Practical work and leadership.

Experience track

ML Research Intern

Under Prof. Ruchi Sherawat

June 2025 - August 2025

Built a dental RGB image classification system for age and gender prediction. The project covered preprocessing, masking, training, evaluation, and model comparison to identify the strongest pretrained approach.

Experience track

AI / ML Team Lead

Google Developer Students Club, USICT

October 2024 - Present

Leading AI / ML initiatives, mentoring project work, and shaping practical experimentation across student-driven builds.

Build Projects and Demos

Screenshot of the TaxAI India website

TaxAI India

A hybrid tax assistant for Indian freelancers, students, creators, and small businesses that combines AI reasoning with deterministic tax logic, document extraction, and compliance insights.

  • AI copilot for tax planning and compliance guidance
  • OCR-based financial document extraction and structured analysis
  • Old vs new regime comparison with optimization insights
FastAPIReactMongoDBLangChainOCR
Screenshot of the CallBased Product Retrieval Agent website

CallBased Product Retrieval Agent

An AI-powered calling agent that helps customers find products through natural phone conversations. Built with Twilio, ElevenLabs, Groq LLM, and ChromaDB with semantic search plus metadata filters.

  • Voice conversation flow for product discovery
  • Semantic retrieval with budget, brand, and category filters
  • User preference memory for better follow-up turns
TwilioElevenLabsGroqChromaDBRetrieval

Get in Touch

Want to chat? Feel free to reach out to me via email or on social media.