Building intelligent AI systems that reason, collaborate, and automate real-world workflows.

Portfolio • LinkedIn • Email

I’m a Master’s student in Automation Engineering at the University of Bologna (Italy) with a strong focus on Generative AI, LLM engineering, and intelligent automation.

My work revolves around designing production-grade AI systems, from multi-agent workflows and self-correcting RAG pipelines to LLM evaluation frameworks and full-stack GenAI applications.

I enjoy bridging research-grade AI concepts with real-world engineering, building systems that are:

• Modular
• Scalable
• Observable
• Actually deployable

• Multi-Agent AI Systems
  Role-based agents (Researcher, Coder, Manager, Evaluator) collaborating using LangGraph and structured reasoning.

• LLM-as-Judge & Evaluation Pipelines
  Automated A/B testing, rubric-based scoring, creativity & factuality evaluation of model outputs.

• Advanced RAG Architectures
  Self-correcting RAG, retrieval validation loops, hybrid embeddings, and vector-DB-driven knowledge engines.

• LLM Fine-Tuning & Optimization
  LoRA fine-tuning on domain-specific datasets (TinyLlama, Llama, Mistral) with efficient inference pipelines.

• End-to-End GenAI Products
  Full-stack AI apps using FastAPI, Streamlit, LangChain, LangGraph, Groq LLMs, and cloud-ready deployments.

• Multi-Agent Research Team – Autonomous research, summarization & report generation
• LLM-as-Judge – LLM-powered evaluation & benchmarking system
• Self-Correcting RAG – Multi-agent RAG with answer validation
• AI Workflow Assistant – CSV-driven reasoning & analytics agent
• Multi-Agent Marketing Workflow – End-to-end campaign generation using Groq LLMs
• Adversarial ML Projects – LunarLander & CelebA adversarial robustness experiments

• PyTorch, TensorFlow, Scikit-Learn
• LangChain, LangGraph, HuggingFace
• Prompt Engineering, RAG, Multi-Agent Systems
• LoRA, Fine-Tuning, Model Evaluation
• Groq API, OpenAI-compatible APIs

• Pandas, NumPy, Matplotlib, Seaborn
• Statistical Analysis, Time-Series, EDA
• Power BI, Predictive Analytics

• FastAPI, REST APIs
• React, Streamlit
• SQL (Postgres, MySQL), MongoDB
• Docker, Git, Linux

• Jupyter, VS Code
• CI/CD basics, modular architectures

• LLM automation & agentic systems
• RAG pipelines & enterprise search
• Model evaluation frameworks
• GenAI product MVPs & prototypes
• Research-to-production AI systems

LLMs • RAG • Multi-Agent Systems • LangChain • LangGraph • Groq • Prompt Engineering • LLM Evaluation • Fine-Tuning • FastAPI • Streamlit • GenAI Architecture

• 🌍 Website: https://syedwaleedahmed.me
• 📄 Resume: https://drive.google.com/file/d/1jkVZ_N2QvQBWRvf9vnzDBfgR0_zGfM0p/view?usp=sharing

I design systems where AI agents argue, critique each other, and converge on better answers, basically turning chaos into intelligence 🤖