AI Engineer | Multi Agent Systems & LLM Applications I build AI agents that leave the whiteboard and actually ship to production.
📍 Munich / Erlangen, Germany · 📧 alam.ayaz47@gmail.com LinkedIn • GitHub • Portfolio • Hugging Face
A multi LLM experimentation platform for running, comparing, and interacting with different AI models through a unified interface with real time streaming.
A product for creating personal messages that are meant to be opened at the right moment, making simple messages feel more thoughtful and memorable.
I'm an AI Engineer who gets genuinely excited about making multi agent systems reliable enough for the real world, not just clever demos.
Over the past two years, I've worked across applied machine learning, enterprise AI, and production software engineering. I have worked with more than 90M labor market records at IAB, built production grade multi agent frameworks for Siemens Energy, and shipped agentic procurement systems at Zalion GmbH.
Outside of work, I build my own products through Ilham Labs.ai, experiment with LLM systems, and sometimes work on projects simply because they seem interesting. One of those projects was fine tuning GPT 2 to write poetry.
• 🏭 Built a production multi agent framework for Siemens Energy with persistent state, audit ready execution, and human in the loop safety controls
• 🤖 Built production grade multi agent procurement systems using LangGraph, LangChain, FastAPI, PostgreSQL, and AWS
• 📊 Applied ML including XGBoost, Random Forest, SVM, and PU Learning across 90M+ records
• 🚀 Founded Ilham Labs.ai, an independent AI product studio building AI powered applications and developer tools
• 🧩 Currently building Lattice Lab, a multi LLM experimentation platform
• 💌 Currently building WhenYouOpen.me, a personal messaging product
• 🎨 Fine tuned GPT 2 with reinforcement learning to write poetry, with 3,600+ downloads on Hugging Face
Mar 2026 to Jul 2026
• Built production grade multi agent procurement systems using LangGraph, LangChain, FastAPI, PostgreSQL, Next.js, and AWS
• Developed agentic workflows for procurement processes including RFQ generation, supplier selection, and structured request handling
• Improved agent reliability through prompt engineering, structured validation, persistent workflows, and human in the loop patterns
• Worked across the full stack, including AI orchestration, backend APIs, frontend features, infrastructure, and CI/CD deployment
Jul 2025 to Feb 2026
• Designed an enterprise multi agent framework with persistent memory, modular agent orchestration, and audit ready execution for industrial AI use cases
• Built AI assistants for engineering knowledge retrieval, log analysis, and report generation
• Implemented human in the loop safety controls and structured execution workflows for reliable enterprise deployment
• Worked with LangGraph, LangChain, FastAPI, PostgreSQL, vector retrieval, and LLM based agent architectures
Nov 2024 to Feb 2026
• Applied XGBoost, Random Forest, SVM, and Positive Unlabeled Learning across 90M+ employment records to model labor market trends
• Built scalable ML pipelines for feature engineering, model evaluation, classification, and job matching predictions
• Worked on large scale occupational classification and skill analysis using machine learning and explainability techniques
Apr 2025 to Jul 2025
• Built AI agents for automated data validation and quality assessment across business use cases
• Developed Generative AI tools and internal productivity applications to support enterprise workflows
• Worked across data engineering, AI prototyping, and business facing consulting
Multi LLM Experimentation Platform
A platform for experimenting with and comparing multiple LLMs through a unified interface, with real time streaming and model orchestration.
React · FastAPI · PostgreSQL · Redis · LLMs · Docker
Personal Messaging Product
A product built around creating meaningful messages for specific moments and experiences.
Independent AI Product Studio
A personal product studio where I build and experiment with AI applications, LLM infrastructure, developer tools, and product ideas.
AI & Agents LangGraph · LangChain · LLM Applications · Multi Agent Systems · RAG · Prompt Engineering · Human in the Loop
Machine Learning XGBoost · Random Forest · SVM · PU Learning · Scikit learn · Model Evaluation · SHAP
Backend & Infrastructure Python · FastAPI · PostgreSQL · Redis · Docker · AWS · REST APIs · SSE · CI/CD
Frontend React · Next.js · Flutter
MSc Data Science Friedrich Alexander Universität Erlangen Nürnberg 2022 to Present
I'm interested in building AI systems that actually work outside a notebook, especially multi agent systems, LLM applications, AI infrastructure, and end to end AI products.
Always happy to talk about AI engineering, interesting products, or new opportunities.