Currently: Home Lab Expansion & Local LLM Benchmarking

PRAKASH
SINGH

$

I build complete systems end-to-end — from training CNNs on 9,000-image datasets and deploying quantized models to edge hardware, to self-hosting my own cloud infrastructure with Docker, DDNS, and reverse proxies. I ship real solutions.

01 // about

About

I'm a 2nd-year B.Tech student who builds complete systems, not demos.

My focus sits at the intersection of deep learning, edge deployment, and self-hosted infrastructure. I've trained CNN pipelines on 9,000+ image datasets, quantized models to INT8 for NXP edge hardware, and shipped Dockerized workflows running on my own home lab.

I prefer measurable wins — accuracy numbers, hackathon results, deployed systems — over surface-level prototypes. Currently expanding my home lab and benchmarking local LLMs.

Education: B.Tech, GL Bajaj Institute of Technology (Expected 2028) — 2nd Year
Location: Greater Noida, India
2
Hackathon Wins
9,000+
Training Images
86.6%
Model Accuracy
12+
GitHub Repos
02 // skills

Skills

The toolchain behind the systems I ship.

Languages

PythonCC++JavaJavaScriptTypeScriptHTMLCSSBash

AI / Machine Learning

Computer VisionCNNsMobileNetV2Transfer LearningFocal LossData AugmentationEdge AITensorFlowTFLiteKerasGoogle ColabKaggle

Agentic & Local AI

LLM AgentsTool CallingPrompt EngineeringOllamallama.cppLM StudioLangChainOffline AI Systems

Generative AI

Stable DiffusionSD WebUISynthetic Data GenerationPrompt Engineering

Infrastructure & Systems

DockerLinuxNginxReverse ProxyDDNSPort ForwardingSelf-HostingNextcloudHome ServerDual Boot

Dev Tools & Web

GitVS CodeREST APIsTailwind CSSNode.jsGCPVercel

Core CS

Data StructuresAlgorithmsProblem DecompositionOOP
03 // selected_work

Selected Work

End-to-end systems shipped to real users and real hardware.

🏅 DeepTech Grand Finalist

Forsaken-Apex

Production Semiconductor Defect Detection AI

Production-ready deep learning pipeline for automated semiconductor wafer defect detection. Classifies 8 defect types with 86.6% accuracy.

  • Trained on 9,000+ image dataset with synthetic augmentation via Stable Diffusion
  • MobileNetV2 + Squeeze-and-Excitation (SE) Attention architecture
  • Focal Loss training for class imbalance handling
  • INT8 quantization for edge deployment on NXP hardware (TFLite)
TensorFlowKerasPythonMobileNetV2Stable DiffusionTFLiteEdge AI
View Project

DualZen

Cross-Platform Browser Workspace Sync

Syncs pinned tabs, tab groups, and workspace organization between two Zen Browser instances across dual-boot machines using Google Drive.

PythonJavaScriptBrowser ExtensionsGoogle Drive API
View Project
🥈 2nd Place

QuarryFlow-Crossing

Constraint-Driven Data Pipeline

Built under strict competition constraints at KnowledgeQuarry — focused on correctness, efficiency, and clean problem decomposition under time pressure.

PythonAlgorithmsData Processing
View Project
🥇 1st Place

VisualizeSim

Simulation Visualization System

Award-winning simulation visualization tool for interpreting complex datasets with focus on clarity and cognitive accessibility.

PythonData VisualizationUI/UX
View Project

Critical-Mass

AI Bot for Chain Reaction Board Game

Highly optimized AI game bot featuring alpha-beta search engine with pruning and a reinforcement learning training pipeline.

PythonReinforcement LearningAlpha-Beta SearchGame AI
View Project

openenv-vendor-compliance

Deterministic Vendor Compliance Workflow

OpenEnv environment for deterministic vendor onboarding and compliance review with Docker-based reproducibility.

PythonDockerComplianceYAML
View Project

Mocktasium

AI-Powered Mock Test Platform

Responsive web application with AI-driven test generation and evaluation. Intelligent scoring, analytics dashboard, and adaptive question generation.

JavaScriptTailwind CSSAI IntegrationREST APIs
04 // achievements

Achievements

Hackathon trophies and competitive recognitions.

🥇
1st Place
VisualSim Hackathon
Mirabilis Design

Built VisualizeSim, a simulation visualization system for interpreting complex datasets.

🥈
2nd Place
KnowledgeQuarry
Delhi University

Developed QuarryFlow Crossing under strict constraints — correctness & efficiency focused.

🏅
Grand Finalist
DeepTech Hackathon
IESA

Production semiconductor defect detection AI pipeline deployed to NXP edge hardware.

🎖️
Rank 1
National Cyber Olympiad
School Level

National recognition in cybersecurity competition.

05 // experience_&_training

Experience & Training

AI Model Development

  • Trained models on Google Colab & Kaggle GPU environments
  • Built dataset curation, augmentation, and benchmarking pipelines
  • Optimized models for edge deployment via INT8 quantization (TFLite)

Local AI & Self-Hosting

  • Built offline AI pipelines and LLM assistants (llama.cpp, Ollama, LM Studio)
  • Configured home servers, port forwarding, DDNS, and Docker hosting
  • Automated workflows using AI-CLI tools and shell scripting

// Certifications

Python & TensorFlow: Deep Dive
Udemy
2026
C++ for Beginners
Udemy
2026
DeepTech Hackathon Finalist
IESA
Data Analyst 101
Simplilearn
2025

Half of what I actually know came from breaking things at 2am, not from these. But the paper helps.

06 // get_in_touch

Get In Touch

Open to internships, collaborations, and interesting systems problems.

Drop a message about an idea, an opportunity, or a build you want help with. I read everything and reply quickly.