Available for opportunities

Md Shoaib
Shahriar
Ibrahim

AI Engineer with professional experience developing LLM-based software analysis systems, multi-agent workflows, RAG pipelines, and FastAPI backend services. Skilled in building AI systems for code analysis, repository metadata processing, retrieval-augmented generation, query routing, reranking, guardrails, caching, and Dockerized deployment. Experienced in applying LLMs and automation to improve software vulnerability analysis, document-based decision support, enterprise knowledge retrieval, conversational workflows, and deep learning applications.

01

Experience

Software Engineer (ML)
OpenRefactory, Inc. — USA
Dec 2024 – Present
  • Contributed to an LLM-powered microservice for automated root-cause analysis of software vulnerabilities (CVEs), using multi-agent systems and prompt engineering to improve code-level insights.
  • Designed and implemented data pipelines to retrieve, parse, and process commit metadata using REST APIs and web scraping.
  • Developed the Builder Project, a multi-agent AI system that analyzes GitHub READMEs and generates optimized Dockerfiles through LLM orchestration and build requirement extraction.
Data Science Trainee
Mastercourse IT — Bangladesh
Apr 2023 – Dec 2023
  • Completed an intensive internship covering Data Analytics, NLP, Machine Learning, and Deep Learning.
  • Delivered four end-to-end industry-style projects involving data preprocessing, model development, evaluation, and deployment-focused workflows.
02

Projects

2025
TakaSecure — Secure Banking Policy Intelligence with Fine-Tuned LLM and Adaptive RAG

Fine-tuned Llama 3.1 8B (QLoRA + Unsloth) on 7,000 synthetic examples, achieving 1.00 citation recall and 96.6% JSON accuracy, deployed via self-hosted vLLM for privacy-preserving policy assistance. Built an adaptive LangGraph RAG pipeline (FastAPI, hybrid Qdrant retrieval, cross-encoder reranking, corrective Self-RAG, fail-closed answer verification, Redis caching) achieving 1.00 RAGAS faithfulness and context recall.

LangGraph QLoRA vLLM Qdrant Self-RAG
2025
AI Claims Processing System — Advanced RAG for Insurance Claim Adjudication

AI-powered claims platform that reduces slow, manual insurance review by extracting hospital invoice data, auto-filling claim forms, and generating evidence-backed approval, rejection, or human-review reports. Built with FastAPI, LangChain, FAISS, FlashRank, OCR pipelines, Redis caching, and Docker, implementing hybrid BM25 + FAISS retrieval, RRF fusion, reranking, and confidence-gated Self-RAG checks.

RAG FAISS OCR FlashRank Docker
2025
BusGo — Banglish AI Bus Ticket Booking Platform

AI-powered Banglish chatbot platform that reduces the hassle of traditional bus ticket booking by helping Bangladeshi users search, compare, and book tickets through natural conversation. Built with FastAPI, SQLite, Gemini, LangChain, ChromaDB, and Docker, implementing RAG with MMR retrieval, query rewriting, exact route lookup, and provider policy enrichment for route, fare, schedule, and policy queries.

RAG LangChain Gemini ChromaDB Docker
03

Skills

Programming
Python C C++
Backend & Databases
FastAPI SQLite MySQL SQL Oracle Jinja2
LLM & RAG Systems
LangChain LangGraph RAG Agentic AI Tool-Calling Agents FAISS ChromaDB Vector Databases
Deep Learning & NLP
PyTorch TensorFlow Keras Scikit-learn Transformers Fine-Tuning Transfer Learning
Infrastructure & Monitoring
Docker Docker Compose Redis LangSmith
Web Scraping
BeautifulSoup Selenium REST APIs
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.