Back home
Work

Projects and experiments.

Things I've built to understand distributed systems, protocols, and the tradeoffs behind reliable software.

Protocol Engineering2026

MAVLink v2 Telemetry Recorder

An embedded-style C++17 learning project that reconstructs MAVLink v2 frames from a byte stream, decodes selected UAV messages, and records human-readable telemetry to CSV.

C++17MAVLink v2CMakeFinite State MachineCRC-16/X.25Binary Protocol Parsing
View case study →
AI Systems2024

AI Multi-Agent Orchestration Platform

A production agentic system that decomposes complex tasks, dispatches specialised agents, maintains working memory, and routes tool calls through a typed execution graph.

PythonLangGraphClaudepgvectorFastAPI
View case study →
AI Systems2024

Production RAG Infrastructure for Document Intelligence

End-to-end retrieval-augmented generation pipeline with hybrid dense-sparse retrieval, MMR reranking, and a streaming inference layer. Deployed for a fintech firm with 40K+ document corpus.

Pythontext-embedding-3-smallpgvectorFastAPINext.js
View case study →
Tooling2023

LLM Evaluation Harness

Framework for evaluating language model outputs across factuality, format adherence, and task-specific rubrics. Designed to be extended as models change, not replaced.

PythonTypeScriptPydanticpytest
View case study →
AI Systems2023

UPI Transaction Fraud Detection System

Real-time fraud detection pipeline for UPI payment flows, processing 50K+ transactions per minute at sub-100ms decision latency using a tiered rule-based and ML classifier architecture.

PythonFastAPIRedisPostgreSQLscikit-learn
View case study →
Product2024

Enterprise Knowledge Search - Context Engine

Semantic search and document intelligence layer across 200K+ internal documents, with natural language queries, role-based access filtering, and a streaming answer interface.

PythonNext.jsTypeScriptOpenAIpgvectorFastAPI
View case study →