Models Skills AI Footprint Projects Experience Certs Contact Resume ↓
Open to AI opportunities

Syed SarimAhsan

AI Engineer · LLM Systems & Agentic Workflows · SSUET

I build practical AI products end-to-end: fine-tuned Hugging Face models, corrective RAG systems, and real-world multi-agent platforms. From model training to deployment, I focus on AI that delivers measurable outcomes.

0 HF Models
0 Projects
0 MCP Servers
Sarim Ahsan
Place profile image here
Sarim Ahsan
AI / ML Engineer · SSUET
Available
sarim@ai-engineer ~ /profile
whoami
AI Engineer · Fine-tuning · Agentic AI · Production

models --recent
→ TinyLlama-1.1B-Alpaca-QLoRA · qwen2.5-7b-thinking-esp
→ opt-125m-alpaca-qlora · medical_symptom_transformer
→ xray_disease_cnn_model

agents --mcp
→ psx-mcp-claude · github-mcp-claude

status
🟢 Open to Internships & Full-time Roles

PythonPyTorchTensorFlowLangChainRAGLangGraphFastAPIHuggingFaceReactDockerKubernetesFAISSLoRA · QLoRADPO · GRPOMulti-AgentGroqTavilyQdrantChromaDBNode.jsMongoDBMySQLNginxGitHub ActionsTransformersOpenCVFine-tuningVector DBs PythonPyTorchTensorFlowLangChainRAGLangGraphFastAPIHuggingFaceReactDockerKubernetesFAISSLoRA · QLoRADPO · GRPOMulti-AgentGroqTavilyQdrantChromaDBNode.jsMongoDBMySQLNginxGitHub ActionsTransformersOpenCVFine-tuningVector DBs
Hugging Face Portfolio

Fine-Tuned Model Lab

Selected models I have trained and fine-tuned for real use cases in instruction following, reasoning, and medical AI.

Text Generation1B
sarimahsan101/TinyLlama-1.1B-Alpaca-QLoRA

TinyLlama Alpaca QLoRA

Instruction-tuned TinyLlama optimized with QLoRA for efficient deployment and lightweight inference workflows.

Fine-TunedQLoRAInstruction
View model →
Text Generation8B
sarimahsan101/qwen2.5-7b-thinking-esp

Qwen Thinking ESP

Reasoning-oriented fine-tuned Qwen variant designed for stronger thought-structured responses in complex prompts.

Fine-TunedReasoning54+ Likes
View model →
Text Generation0.2B
sarimahsan101/opt-125m-alpaca-qlora

OPT-125M Alpaca QLoRA

Compact instruction model fine-tuned for low-resource experimentation and fast-turnaround prototyping.

Fine-TunedSmall ModelAlpaca
View model →
Medical NLP0.1B
sarimahsan101/medical_symptom_transformer

Medical Symptom Transformer

Domain-focused medical model for symptom understanding and condition-focused inference pipelines.

Healthcare AINLPTransformer
View model →
Computer VisionCNN
sarimahsan101/xray_disease_cnn_model

X-Ray Disease CNN

Custom CNN pipeline built for medical image classification and disease-focused X-ray prediction tasks.

Healthcare AICNNVision
View model →
What I do

Technical Arsenal

Multi-Agent & Agentic AI
Designing orchestrated multi-agent pipelines using LangGraph for complex, stateful workflows. Building production agentic systems with tool-calling, memory, and real-world integrations.
LangGraph LangChain Groq Tavily Tool Calling FastAPI
RAG & LLM Systems
Building production RAG pipelines with semantic search, hybrid retrieval, and reranking. Experience with Qdrant, ChromaDB, FAISS, and pgvector for vector storage.
RAG Qdrant ChromaDB FAISS Gemini API OpenAI API
LLM Fine-tuning
End-to-end fine-tuning pipelines from LoRA through GRPO. Practical experience with PEFT, quantisation, and alignment techniques using HuggingFace TRL and bitsandbytes.
LoRA / QLoRA DPO GRPO PEFT TRL bitsandbytes
Deep Learning & ML
Designing and training models from scratch — CNNs, transformers, and classical ML. Hands-on with real datasets, Kaggle competitions, and federated learning research.
PyTorch TensorFlow Scikit-learn CNNs Transformers HuggingFace
Full Stack Engineering
End-to-end web apps with React/Vite, FastAPI, Node.js, MySQL, and MongoDB. Two live production deployments serving real users with CI/CD pipelines and automated backups.
FastAPI React / Vite Node.js MySQL MongoDB REST APIs
DevOps & Infrastructure
Managing VPS deployments with Docker Compose, Nginx reverse proxy, GitHub Actions CI/CD, and automated backup scripts with email notifications. Two live apps in production.
Docker Nginx Linux VPS GitHub Actions Kubernetes Vultr
Proof of Work

AI Footprint

Kaggle

Curated Research Notebooks

Selected notebooks from my public Kaggle work focused on modeling, reasoning, and practical experimentation.

  • Train your own R1 reasoning model with Unsloth
  • GSPO Fine-tuning on GSM8K
  • Ensemble Methods Battle
  • HousePrices Comprehensive EDA & Modeling
  • X-ray CNN model experiments
View Kaggle workspace →
GitHub

AMD AI Academy Track

Notebook collection covering vLLM serving, diffusion pipelines, and GPU-accelerated inference workflows on AMD MI300X.

  • Repository: amd-ai-learning
  • Practical model serving workflows
  • Hands-on inference optimization labs
Open repository →
MCP Agents

Developer Tooling I Built

Two JavaScript MCP servers built to give LLMs live tooling access for market intelligence and developer workflows.

  • psx-mcp-claude: live Pakistan Stock Exchange data
  • github-mcp-claude: read-only GitHub analysis server
What I've built

Featured Projects

02
Corrective RAG · Finance · Production
MeezanGPT — Corrective RAG Chatbot

Advanced Islamic banking chatbot built on Corrective RAG (CRAG) — a self-verifying pipeline that crawls target websites, chunks and embeds content, retrieves relevant context, then runs a corrective layer that cross-checks generated answers against retrieved documents to eliminate hallucinations. Built for finance and banking use cases like policy lookups and FAQs.

Corrective RAG FAISS / Pinecone OpenAI / LLaMA BeautifulSoup PyPDF2 FastAPI Python
03
AI Tool · RAG · Full-Stack
ArXiv Lens

AI-powered research tool that summarizes ArXiv papers, builds citation knowledge graphs, and lets you chat with any paper using RAG — built with FastAPI, HuggingFace, ChromaDB, and React with an animated glass-morphism UI.

FastAPIReactHuggingFaceChromaDBRAGGroq
04
RAG · Dataset · Open Source
LexCorp Legal RAG Dataset

A synthetic law firm knowledge base for training and evaluating RAG pipelines — covering civil litigation, criminal law, contracts, IP, employment, immigration, tax, bankruptcy, and legal ethics. Designed as a benchmark dataset for legal AI systems.

PythonRAGLangChainFAISSNLPDataset
05
Medical AI · NLP + Vision
Doctor AI — MediChat

Web-based symptom checker where users describe symptoms in natural language or upload X-ray images to receive AI-powered condition predictions with confidence scores — returning top 1, 3, or 5 diagnoses via a backend NLP + image classification API.

FastAPIHuggingFaceNLPCNNPython
06
LLM Application
AI Chatbot — Gemini API

Production chatbot powered by the Gemini API with full context management, streaming responses, and a clean conversational UI built with React and FastAPI.

PythonGemini APIReactFastAPI
07
Voice AI Assistant
AI Assistant

Voice-activated AI assistant built on the OpenAI API that handles computer tasks, answers questions, and executes commands based on natural voice input.

Speech RecognitionOpenAI APIPythonTTS
08
Deep Learning
CNN Image Classification

Convolutional neural networks trained and fine-tuned for image classification, including custom architectures and transfer learning with PyTorch and TensorFlow.

PyTorchTensorFlowCNNOpenCV
09
Machine Learning
House Price Prediction

Machine learning models trained to predict house prices based on various features and market trends using regression techniques and feature engineering.

Scikit-learnPandasNumPyMatplotlib
10
Open Source · HuggingFace
Model Hub Contributions

Fine-tuned and published transformer models to the Hugging Face Hub — contributing to the open-source AI ecosystem with reproducible pipelines and PEFT/LoRA fine-tuning methods including LoRA, QLoRA, DPO, and GRPO.

HuggingFaceTransformersPyTorchPEFTLoRA
11
Full-Stack · Live · Production
GCRD Student Portal

Full-stack student management portal built for UK-based company GCRD — features student records, role-based authentication, and a full admin dashboard. Built with React, Express, and SQL. Deployed on VPS with Docker Compose and Nginx.

ReactNode.jsExpressSQLDockerNginx
12
Full-Stack · Live · Production
University Student Hub

A call-centre application providing seamless communication and support for university students — built with a full MERN-style stack and deployed to production with automated CI/CD.

ReactNode.jsExpressSQLDockerGitHub Actions
13
Web App
TODO List App

Full-stack task management application with user authentication, persistent storage, and a clean responsive interface built with React and Node.js.

ReactNode.jsExpressREST API
14
Mobile App · Flutter
Mates Food Delivery App

Cross-platform food delivery app with real-time order tracking, user authentication, and a Firebase Realtime Database backend — built with Flutter and Dart.

FlutterFirebaseDartRealtime DB
Background

Experience & Education

2024–Present
GCRD · UK-BASED COMPANY
Application Support Engineer
Supporting and maintaining the full-stack GCRD Student Portal in production — handling bug fixes, VPS infrastructure management, Docker deployments, database maintenance, and feature updates. Sole technical owner of a live platform serving real users for a UK-based education company.
ReactNode.jsDockerVPSMySQLNginx
2024–Present
UNI STUDENT HUB · UK-BASED COMPANY
Application Support Engineer
End-to-end ownership of the University Student Hub call-centre platform — production deployments via GitHub Actions CI/CD, Docker Compose orchestration, Nginx configuration, automated database backups with Gmail notifications, and ongoing feature development.
ReactExpressGitHub ActionsDockerNginxLinux VPS
2025
IFFCO PAKISTAN · WORLDWIDE COMPANY
IT Intern
Hands-on internship at a global corporation, gaining experience in enterprise IT infrastructure, systems administration, and technical operations at scale.
IT InfrastructureSystems AdminEnterprise
2023–Present
SIR SYED UNIVERSITY OF ENGINEERING & TECHNOLOGY
B.E. Computer Engineering — GPA 3.5
Final year CE student with a deep focus on AI/ML, agentic systems, LLM fine-tuning, and production engineering. FYP in federated learning with quality-aware aggregation. Consistent high-GPA academic performance throughout.
Computer EngineeringGPA 3.5Final YearFederated Learning FYP
2023–2024
COMPETITIVE PROGRAMMING
Meta Hacker Cup · Kaggle Competitions
Participated in Meta Hacker Cup and multiple Kaggle ML competitions, sharpening algorithmic problem-solving and real-world ML skills under pressure.
Meta Hacker CupKaggle170+ LeetCode
Ongoing
HUGGING FACE · OPEN SOURCE
Model Contributor
Fine-tuned and published ML models to the Hugging Face Hub using LoRA, QLoRA, DPO, and GRPO — contributing reproducible experiments and PEFT pipelines to the open-source AI community.
HuggingFaceLoRA / QLoRADPOGRPOPEFT
Credentials

Certifications

DATACAMP
Associate Data Scientist Certification
DEEPLEARNING.AI / STANFORD UNIVERSITY
Machine Learning Specialization
MEDIUM
Technical AI/ML Writing & Publications
Curriculum Vitae
Want the full picture?

My resume covers everything — projects, experience, skills, and certifications — in one clean document. Download it or preview it right in your browser.

Get in touch

Let's Connect

Open to AI/ML engineering roles, research collaborations, and interesting projects. Based in Karachi, Pakistan.

Send a Message