Skip to content
View A-ES's full-sized avatar

Highlights

  • Pro

Block or report A-ES

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
A-ES/README.md

Mohammed Abrar

AI Engineer • Autonomous AI Agents • LLM Systems • RAG • DevOps Automation

Building intelligent systems that reason, retrieve context, and automate complex engineering workflows.


👋 About Me

I'm an AI Engineer passionate about building autonomous systems that extend the capabilities of Large Language Models beyond conversation.

My work focuses on combining LLMs, Retrieval-Augmented Generation (RAG), vector search, and workflow orchestration to create AI systems that understand context, make decisions, and interact with real software infrastructure.

I enjoy solving engineering problems where AI can automate repetitive workflows, accelerate developer productivity, and operate reliably in production environments.


🚀 Featured Projects

Autonomous CI/CD Remediation Agent

A production-oriented multi-agent system that automatically diagnoses GitHub Actions failures, retrieves similar historical incidents using vector search, generates fixes, and opens pull requests with minimal human intervention.

Highlights

  • LangGraph-based autonomous workflow
  • Repository Structure Index (RSI) for repository understanding
  • Episodic memory using PostgreSQL + pgvector
  • Few-shot RAG for failure diagnosis
  • Dockerized deployment with GitHub webhook integration

Impact

  • 🚀 Reduced debugging time by 65%
  • 🤖 Automatically resolved 60–75% of common CI/CD failures

NLP-Driven Feedback-to-Code Automation Pipeline

Built an end-to-end system that transforms raw user feedback into actionable engineering tasks using NLP clustering and semantic similarity.

Highlights

  • Chrome Extension + CLI Agent + Dashboard
  • Semantic clustering using cosine similarity
  • Automatic code module mapping
  • Intelligent feedback deduplication

Impact

  • ⚡ Reduced manual code-update effort by 40%
  • 🚀 Reduced feedback-to-deployment cycle from hours to under 10 minutes

🛠 Tech Stack

AI & Machine Learning

PythonOpenAI APILangChainLangGraphRAGPrompt EngineeringVector SearchpgvectorScikit-learnNLP

Backend

FastAPINode.jsExpress.jsREST APIsWebSocketsSSE

Frontend

ReactJavaScriptTypeScriptHTMLCSS

Databases

PostgreSQLMongoDBMySQL

DevOps & Cloud

DockerGitHub ActionsGitAWSAzureGCP


🏆 Achievements

  • 🥇 Winner — Code and Solve Challenge
  • 🥇 Winner — Hack to Future
  • 🏅 Top 6 — Agentathon (PES University)
  • 💻 Solved 300+ LeetCode problems
  • 📈 LeetCode Max Rating: 1564

📊 GitHub Stats


🤝 Connect

I'm always interested in collaborating on projects involving:

  • Autonomous AI Agents
  • LLM Applications
  • Retrieval-Augmented Generation (RAG)
  • AI Infrastructure
  • Developer Tools
  • Open Source AI

If you're building in this space, feel free to reach out!

Building autonomous software that transforms AI from an assistant into an engineering teammate.

Pinned Loading

  1. DevOps_proejct DevOps_proejct Public

    Python 1

  2. hacktofuture4-I08 hacktofuture4-I08 Public

    Forked from hacktofuture-sjec/hacktofuture4

    Python 1

  3. NoobieDYG/R3GE-CrowdFlow NoobieDYG/R3GE-CrowdFlow Public

    Python 1

  4. AI_Agent AI_Agent Public

    JavaScript