guest@lakshay:~$ whoami

Lakshay
Systems & AI Architect

IIT Delhi '27 • Civil Engineering • Computer Science Minor
Building robust systems from the ground up—from Unix shells and high-performance Redis clones to Agentic RAG pipelines and LLM evaluation frameworks.

Github LinkedIn Email

The Systems Forge

High-Performance Redis Clone

Low-latency, in-memory KV store built with raw C++. Implements RESP protocol, non-blocking I/O with poll/epoll, and AOF/RDB persistence.

C++17NetworkingSystem Design
READ BLUEPRINT

Custom Unix-like Shell

POSIX-compliant shell with process lifecycle management (fork/exec), pipelines, signal handling, and I/O redirection.

CLinux KernelPOSIX
VIEW SOURCE

Edge AI Optimization Pipeline

Optimized YOLOv8-tiny for edge hardware using TensorRT INT8 quantization, achieving 128 FPS on Jetson-based GPUs.

TensorRTONNXCUDA
BENCHMARKS

The AI Lab

Agentic RAG System

Autonomous pipeline using LangChain and FAISS for complex document understanding and multi-step reasoning.

PythonLangChainFAISS
EXPLORE ARCHITECTURE

LLM Evaluation Framework

Lightweight framework to benchmark model reasoning, instruction-following, and hallucination detection.

PyTorchLLM BenchmarkingAnalytics
CASE STUDY

Transformer From Scratch

Decoder-only Transformer implementation (multi-head attention, causal masking) with training stability analysis.

PyTorchCUDAArchitecture
READ DOCS

The Application Layer

ShopSphere (Flash Sale Engine)

Industrial-grade ordering system handling 1,000+ RPS with Redis-based distributed locking and RabbitMQ queues.

MERN StackRedisPostgreSQL
LOAD TEST DATA

Mini-Vercel Deployment Platform

Automated cloud platform that builds and hosts sites from GitHub via Docker and a custom reverse proxy.

DockerNode.jsNginx
LIVE DEMO

Technical Toolkit

Languages

  • C / C++ (C++17)
  • Python (PyTorch/DL)
  • JavaScript / TypeScript
  • SQL

Systems

  • Linux (Debian/Bash)
  • Docker & Containers
  • Redis / PostgreSQL
  • Distributed Systems

AI Research

  • RAG Architectures
  • LLM Benchmarking
  • Fine-tuning (LoRA)
  • Vector Databases

Design Tools

  • Unity Engine
  • System Thinking
  • Technical Writing
  • Rapid Prototyping