A collection of data engineering projects, ML systems, and research explorations.
research, Statistics
Building a complete experimentation framework — from hypothesis testing to Bayesian inference
projects
A deep dive into e-commerce data using K-Means clustering to uncover the hidden relationship between delivery performance and customer retention.
research, ML
Understanding the mathematics of reducing high-dimensional data — from eigendecomposition to manifold learning
research, ML
Implementing core ML algorithms from first principles using only NumPy
data engineering, projects
Building a scalable recommendation engine with Lambda Architecture, Kafka, Flink, and Airflow
projects, software engineering
Building an opportunistic data offload system using ESP32 and Raspberry Pi Pico to extract diagnostic telemetry from trains on the 740km Konkan route where LTE is absent for hours at a time
data engineering, projects
Building an enterprise-grade Retrieval-Augmented Generation system with dbt, Qdrant, and LangChain
AI engineering, projects
Building a compliance-ready retrieval-augmented generation system for regulated professional services — and why document-level access controls, immutable audit logs, and data residency matter more than retrieval quality
projects, software engineering
Designing a browser-based audiobook player with IndexedDB storage, chapter extraction, and a Nothing OS-inspired aesthetic — and why the web platform is underestimated for offline applications
projects, AI engineering
Building an AI-powered study planner with a tamagotchi-style farm game — the AI generates daily plans from your materials, the Grove dies if you skip, and verification ensures you actually learned something
projects, software engineering
Designing a terminal trading interface with Rust and ratatui — why a TUI makes sense for real-time data, the architecture of a multi-model ensemble system, and the case for Rust in a data-intensive application
projects, software engineering
Building a YAML-driven resume generator with Jinja2 templating and Tectonic LaTeX — and why separating content from presentation is the most maintainable approach to any document pipeline
No projects found in this category.