Muhammad Ammar

Data Analytics Researcher @ Siemens | MSc Electromobility-ACES @ FAU | Agentic AI & Graph Analytics

Erlangen, Bavaria, Germany

LinkedIn
MA

About

Pursuing an MSc in Electromobility-ACES at Friedrich-Alexander-Universität Erlangen-Nürnberg while working as a Data Analytics Researcher at Siemens. My work focuses on GenAI-enabled software ecosystem health monitoring, graph analytics, Text-to-Cypher pipelines, prompt-to-visualization workflows, and agentic AI systems research.

Work Experience

Siemens AG + FAPS FAU
Erlangen
Research

May 2026 - Present

Master's Thesis

  • Beyond the Agent: A Workflow-Level Review of Agentic AI Systems.
  • Research objective: How are agentic AI systems structured, controlled, and evaluated as end-to-end workflows, and where do current approaches lack system-level rigor?

    • Siemens AG
    Erlangen
    Hybrid

    Oct 2024 - Present

    Data Analytics Researcher - Working Student

  • Conducted systematic literature review of software ecosystem health analysis. Surveyed 61 research articles and analyzed 416 health metrics to present a unified graph of metrics to measure ecosystem health in a hierarchical way.
  • Developed an LLM-based Text-to-Cypher pipeline for analyzing software ecosystem health using a health metric KPI tree.
  • Created a metric graph to oversee real-time visualization of the underlying Neo4j database.
  • Developed an LLM-powered Prompt-to-Visualization pipeline to display the most relevant dashboard for a user query, lowering TTI from 2 minutes to 5 seconds.
  • Submitted 6 invention disclosures and authored 4 research papers.

    • FAPS FAU
    Erlangen
    Research

    Oct 2025 - Mar 2026

    Project Thesis

  • Architectural Paradigms of Multi-Agent Systems and Agentic AI in Intelligent Manufacturing Systems, A Systematic Literature Review.
  • Research objective: How have agent architectures evolved in manufacturing systems, and what architectural design principles emerge from this evolution that are relevant for manufacturing control?

    • NeuroOceans AI
    Remote

    Jan 2024 - Mar 2024

    Machine Learning Engineer

  • Finetuned multiple audiovisual deepfake detection models and evaluated them on performance metrics.
  • Led the entire pipeline development, from dataset collection and preprocessing to model training and evaluation.

    • Learners.ai
    Remote

    Jul 2023 - Dec 2023

    Solution Analyst

  • Used LangChain and Pinecone to create a GPT-powered RAG chatbot that takes a sales call transcript and generates a sales proposal.
  • Developed a copywriter chatbot using LangChain Agents, tool calling, and a curated knowledge base.
  • Conducted Data Import Analysis for data transfer across CRMs, using excel, SQL and Python.
  • Created Ad campaign effectiveness dashboards in HubSpot and Databox.

    • Robotics and Intelligent Systems Engineering (RISE) Laboratory

    2021 - 2022

    Undergraduate Researcher

  • Engaged in a senior year research project, providing bi-weekly presentations to a supervisory panel.
  • Developed a control algorithm for a mobile robot using Arduino, ultrasonic sensors, IR sensors, and encoders.
  • Successfully secured funding through IGNITE National Grassroots Research Initiative 2022 and obtained funding for AHFE Conference registration fees under the Pakistan and European Unions Horizon 2020 ENHANCE project.

    • Education

    Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)

    2024 - Present
    MSc Electromobility-ACES, current grade: 1.4

    Scuola Superiore Sant'Anna (SSSA)

    2025 - 2025
    AI & Robotics in Extended Reality Seasonal School

    National University of Sciences and Technology (NUST)

    2018 - 2022
    B.Sc. Mechanical Engineering

    Skills

    Python
    PyTorch
    LLMs
    Agentic AI
    Multi-Agent Systems
    Prompt Engineering
    Natural Language Processing
    Graph Analytics
    Neo4j
    Cypher
    LangChain
    Computer Vision
    Machine Learning
    Data Science
    ROS2
    English (C2, IELTS 8.5)

    Projects

    Autonomous Mobile Robot

    A Chain-Driven Live Roller Mechanism for Loading and Unloading Packages on Autonomous Mobile Robots in Warehouses

    Robotics
    Arduino Programming
    Controls
    Design

    Image2Audio app

    Users upload an image, the app generates a caption for the image, creates a short story based on the caption, and then converts the story into audio format.

    OpenAI API
    HuggingFace
    LangChain
    Streamlit
    TTS

    Q&A Chatbot on private data

    Blogpost on Retrieval Augmented Generation (RAG) using ChromaDB, GPT wrapped around LangChain, and private data.

    OpenAI API
    LangChain
    Vector Database
    Blogpost

    Scene Classification

    Finetuned ViT pre-trained on ImageNet for Kaggle Intel Classification Challenge.

    PyTorch
    Computer Vision
    Gradio

    Podcast Summarizer

    Converts podcast audio to text using whisper, uses GPT-3.5 to generate a summary, and uses wikipedia API to display additional information.

    OpenAI API
    Whisper
    Audio2Text
    Streamlit

    Transfer Learning with PyTorch

    Scene classification by fine-tuning pre-trained Vision Transformers (ViT) guide.

    PyTorch
    Vision Transformer
    Blogpost

    Publications

    A Chain-Driven Live Roller Mechanism for Loading and Unloading Packages on Autonomous Mobile Robots in Warehouses.

    Applied Human Factors and Ergonomics (AHFE) Conference, 2022.

    Conference Paper

    Prompt-to-Metric: LLMs and Graph Algorithms for Platform Ecosystem Health Monitoring.

    Explores combining LLMs with graph analytics to monitor platform ecosystems.

    Research Paper
    LLMs

    Towards Data-Driven Real-Time Performance Monitoring of Platform Ecosystems.

    APSEC 2025 Software Engineering in Practice track.

    Conference Paper

    Health and Performance Indicators of Platform Ecosystems: a systematic literature review.

    Systematic literature review outlining health and performance indicators for platform ecosystems.

    Systematic Review

    Schema Injection Strategies for LLM-Based Text-to-Cypher Query Translation: An Empirical Study.

    Studies schema injection strategies for LLM-based Text-to-Cypher query translation. Won Best Paper Award.

    LLMs
    Best Paper Award

    Courses

    Machine Learning Specialization by DeepLearning.AI

    Introduces foundational ML concepts. Covers everything from data analytics using pandas to classification using Neural Nets.

    ML
    numpy
    pandas
    matplotlib

    Natural Language Processing Specialization by DeepLearning.AI

    Deep Dive into NLP. Starts from Classification and Vector spaces, coverts probabilistic models, and eventually moves on to Deep Neural Nets.

    NLP
    LSTMs
    GRUs
    Transformers

    PyTorch for Deep Learning by Zero-to-Mastery

    Complete guide to PyTorch from the fundamentals. Covers everything from the basics to building a Vision Transformer from scratch.

    PyTorch
    Computer Vision

    Generative AI with Large Language Models by DeepLearning.AI

    Covers LLMs for text generation, from pre-training to instruction fine-tuning to RLHF.

    Generative AI
    LLMs

    Robotics: Aerial Robotics by UPenn

    Mechanics of flight and design of quadrotors flying robots. Control and Planning for three dimensional flights.

    Motion Planning
    Robotics
    Quadcopter

    ROS2 For Beginners (ROS Foxy, Humble - 2024)

    Programming fundamentals of Robot Operating System 2 (ROS2) in Python.

    ROS2
    Robotics
    Linux
    Python

    Press ⌘J to open the command menu