Available for opportunities

Md Shoaib
Shahriar
Ibrahim

AI Engineer with hands-on experience in LLM-based systems, RAG pipelines, and multi-agent architectures. Worked on intelligent applications including enterprise chatbots, automated vulnerability analysis, and deep learning-based medical imaging systems. Skilled in Deep Learning, Transformers, and model optimization, with experience building backend APIs using FastAPI.

01

Experience

Software Engineer (ML)
OpenRefactory, Inc. — USA
Dec 2024 – Present
  • Contributed to a microservice for automated root-cause analysis of software vulnerabilities (CVEs) using LLMs, multi-agent systems, and prompt engineering, improving the accuracy and relevance of code-level insights.
  • Designed and implemented data pipelines to retrieve and process commit metadata via REST APIs and web scraping.
  • Developed the Builder Project, a multi-agent AI system that interprets GitHub READMEs and generates optimized Dockerfiles using LLM orchestration for build requirement extraction.
Data Science Trainee
Mastercourse IT
Apr 2023 – Dec 2023
  • Completed an intensive internship in Data Analytics, NLP, Machine Learning, and Deep Learning.
  • Delivered industry-standard results across four end-to-end projects.
02

Projects

2025
FinSolve — Role-Based RAG Chatbot

Role-based RAG chatbot for enterprise knowledge retrieval, enabling employees to query internal documents and HR data through natural language with department-scoped access control. Includes hybrid BM25 + semantic retrieval, cross-encoder reranking, LLM-based query routing, PII guardrails, and hallucination detection.

RAG FastAPI LangSmith Prometheus Grafana
2025
BusGo — RAG-Based Bus Ticket Management

AI-powered bus ticket booking system with a natural language assistant for route search, booking, and fare queries. Built using a RAG pipeline with LangChain, ChromaDB, and Google Gemini, with FastAPI, SQLite, and Docker for application flow and booking management.

RAG LangChain Gemini FastAPI Docker
2025
NeuroScan — Deep Learning Based Brain Tumor Classification

End-to-end MRI brain tumor classification pipeline starting from a custom CNN baseline and progressively improving performance using transfer learning with MobileNetV2 and EfficientNet. Includes Optuna-based hyperparameter tuning, MLflow + DagsHub experiment tracking, Grad-CAM explainability, and ONNX INT8 optimization.

TensorFlow Optuna MLflow ONNX Grad-CAM
2025
Automated HR Management System

Automated HR management system using MCP to streamline LLM-driven interactions with organizational tools, helping simplify internal workflows and task execution through AI-assisted orchestration.

MCP LLM Automation
03

Skills

Languages
Python C C++
LLM & AI Systems
LangChain LangGraph Agentic AI RAG Tool-Calling Agents
Databases
MySQL SQL Oracle Vector Databases
Deep Learning & NLP
PyTorch TensorFlow Keras Scikit-learn Transformers Fine-Tuning Transfer Learning
Backend & Tools
FastAPI Docker SQLite Jinja2 MLflow ONNX
Web Scraping
Selenium BeautifulSoup
04

Education

Bachelor in Computer Science & Engineering
Islamic University of Technology — Gazipur, Bangladesh
2020 – 2024
CGPA: 3.48
Higher Secondary School Certificate (HSC)
The Millennium Stars School and College — Rangpur, Bangladesh
2019
GPA: 5.00
Secondary School Certificate (SSC)
The Millennium Stars School and College — Rangpur, Bangladesh
2017
GPA: 5.00

Let's Build
Something
Together.

Open to AI engineering roles, research collaborations, and meaningful real-world AI problems.