— AI SOFTWARE ENGINEER —

I Build Autonomous AI Systems.

Multi-Agent Swarms · Production RAG · Enterprise Guardrails

View Projects GitHub Portfolio Download CV ↓
🏆 View Oracle Certifications ▾
0% First-Pass Fix Accuracy
0% Prompt Injections Blocked
0 Weeks Relentless Building
0 Oracle Certifications
Scroll to explore
Python FastAPI LLaMA 3 Docker Kubernetes ChromaDB Pytest ReAct Agents RAG Pipelines Prompt Engineering AWS OCI Python FastAPI LLaMA 3 Docker Kubernetes ChromaDB Pytest ReAct Agents RAG Pipelines Prompt Engineering AWS OCI

Not Another Tutorial Follower.

I'm Adarsh Kumar Singh, a B.Tech student who decided to stop watching tutorials and start building real, deployable AI systems from scratch.

Over 14 relentless weeks, I went from Python fundamentals to engineering autonomous multi-agent swarms that fix CI/CD pipelines without human intervention. I didn't follow a bootcamp. I didn't copy boilerplate. I built every line of code, every architecture, every guardrail myself.

The result? A production-grade portfolio that proves I can ship AI systems that solve real, painful engineering problems.

🧠

LLM Architecture

ReAct Loops, Tool Calling, Guardrails, RAG Pipelines

Backend Engineering

FastAPI, SSE Streaming, REST APIs, Pytest

🛡️

Production Security

Prompt Injection Prevention, Scope Guardrails, Model Failover

14 Weeks. Zero Shortcuts.

From print("hello") to autonomous AI agents that write, test, and deploy code.

WEEK 1-2

Python Foundations

Mastered Python, NumPy, and Pandas. Built data processing pipelines from scratch.

PythonNumPyPandas
WEEK 3-4

Machine Learning

Built a Document Risk Prediction system. Feature engineering, hyperparameter tuning, model comparison.

scikit-learnRandom ForestML
WEEK 5-6

Production Python & APIs

Built database-backed REST APIs using FastAPI. Pydantic validation and production deployment patterns.

FastAPISQLPydantic
WEEK 7

LLM APIs

First contact with Large Language Models. Built an LLM Assistant with structured prompting and JSON output.

Groq APILLaMA 3Prompting
WEEK 8-9

RAG System: PersonaDoc

Full Retrieval-Augmented Generation pipeline with ChromaDB, semantic chunking, reranking, and hallucination control.

RAGChromaDBEmbeddings
WEEK 10

AI Agents & Tool Calling

Built multimodal agents with Function Calling. Agents that read files, scrape websites, and execute code.

ReActTool CallingAgents
WEEK 11

LLMOps & Evaluations

Real-time Eval Dashboard with SSE streaming, LLM-as-a-Judge, and automatic Model Failover (70B → 8B).

LLMOpsSSEFailover
WEEK 12

Production Agent + Guardrails

Hardened AI agent with Input/Output guardrails blocking prompt injection and out-of-scope queries.

GuardrailsSecurityEvals
WEEK 13

AI Code Reviewer & Meeting Intel

Automated GitHub PR reviewer and a Meeting Intelligence pipeline extracting decisions and action items.

GitHub APIWhisperNLP
WEEK 14

🚀 The Autonomous DevOps Swarm

The capstone. A multi-agent system that intercepts CI/CD failures, diagnoses bugs, writes patches, runs tests, and opens Pull Requests — all without a human.

Multi-AgentOrchestrationAutonomous

Heavy Hitter Projects.

Not tutorials. Not clones. Real systems solving real problems.

CAPSTONE

Autonomous Self-Healing DevOps Swarm

A multi-agent orchestration framework that intercepts CI/CD pipeline failures, diagnoses root causes, writes code patches, verifies fixes via sandboxed testing, and opens Pull Requests — fully autonomously.

PythonGroqLLaMA 3PytestMulti-Agent

Enterprise Production Agent

A hardened compliance AI agent with Input/Output Guardrails, persistent memory, structured logging, and an LLM-as-a-Judge Evaluation Dashboard with automatic Model Failover routing.

PythonFastAPIGuardrailsLLMOps

PersonaDoc — Production RAG

Upload any PDF. Ask questions. Get cited, accurate answers. Built with ChromaDB vector search, semantic chunking, reranking, and hallucination control.

RAGChromaDBEmbeddingsFastAPI

AI Code Review Service

Submit any GitHub PR URL. Get a structured LLM-powered code review with bugs, security issues, severity ratings, and approval decisions. Connects to real GitHub diffs.

GitHub APILLaMA 3JSON Schema

Technologies I Wield.

AI & Machine Learning

LLMs (LLaMA 3, GPT) RAG Pipelines Multi-Agent Orchestration ReAct Loops AI Guardrails Prompt Engineering LLM-as-a-Judge Evals ChromaDB

Backend & DevOps

Python FastAPI REST APIs Pytest Git & GitHub Server-Sent Events CI/CD Pipelines Docker

Certifications

Oracle GenAI Professional Oracle Data Science IoT & Industrial Automation

Ready to Build Together?

I'm actively seeking AI Engineer and Backend Software Engineer roles.

GitHub Activity

Real-time stats pulled from the GitHub API.

📦 Public Repos
Stars Earned
🔀 Forks
🔥 Recent Commits

Commit Activity — Last 12 Weeks

Less More

Recent Activity

AI PULSE
Loading latest AI news...

Interactive Terminal

Type help to see available commands.

entity@apex-paragon:~
Welcome to APEX-PARAGON v1.0
Type help to get started.
$
AI ENTROPY AI
ENTROPY Online — AI Assistant
ENTITY