IQM Quantum Computers

• Developing and maintaining the Graph-Based Calibration (GBC) framework used for automated calibration of superconducting quantum processors.
• Designing and improving calibration graphs for initial calibration and continuous recalibration of quantum processing units (QPUs).
• Building scalable Python systems using multiprocessing to handle increasing qubit counts and complex calibration workflows.
• Contributing to framework-level architecture decisions to support diverse chip designs and growing system sizes.
• Ensuring robustness, performance, and maintainability of calibration automation software used in production environments.
• Actively researching the integration of AI techniques into quantum calibration and control pipelines.
• Technologies: Python, Multiprocessing, Graph-Based Systems, Quantum Calibration, Superconducting QPUs

Fraunhofer ISI

• Architected a modular Multi-Agent System (MAS) supporting 10+ heterogeneous agents with plug-and-play scalability.
• Integrated GPT-4, LLaMA 2, Claude, and Mistral, achieving 95%+ task completion accuracy.
• Benchmarked LangChain, AutoGPT, CrewAI, and AgentVerse, achieving 30% performance optimization.
• Implemented pub-sub and direct messaging protocols for agent coordination.
• Built a real-time dashboard for monitoring and controlling agent behavior.
• Co-authored a research paper on scalable LLM-based MAS architectures.
• Tools: Python, LLM APIs, Multi-Agent Systems, GitLab, System Architecture

BMW Group

• Contributed to the development of the QUARK framework , an open source framework for BMW-specific quantum and classical hardware applications.
• Collaborated with cross-functional teams to model, evaluate, and optimize quantum applications for automotive use.
• Resolved dependency issues, improved code quality, and ensured adherence to PEP8 standards.
• Enhanced architectural models connecting quantum computing theory to real-world automotive applications.
• Led efforts to improve unit testing for better robustness and coverage.
• Contributed to AI Agent Workflow project, focusing on planning agent optimization and prompt refinement for multi-agent systems.
• Managed technical documentation and Jira tasks to streamline project workflow and tracking.
• Tools: Python, Bash/Shell Scripting, Qiskit, PennyLane, Docker, GitHub Actions, PEP8 & AutoPEP8, Unittest, JIRA, Confluence

SAP

• Error Handling Improvement: Developed an HTML report generator using Go in Azure pipelines, reducing pipeline error identification time by 30% and enhancing operational efficiency.
• API Integration: Integrated a REST API to facilitate error communication with an LLM, increasing error resolution speed by 25%.
• Data Manipulation: Utilized Excel for data tasks, improving data analysis accuracy by 20%.
• Resource Optimization: Designed and implemented a Go-based resource cleanup module, reducing manual workload by 50% and preventing resource wastage.
• Voice-enabled Chatbot Development: Created a voice-enabled chatbot using pyttsx3, SentenceTransformer, and SAP BTP's GPT-4-32k, reducing pipeline query resolution time by 40%.
• Backend Development: Developed a Flask backend to handle voice queries, streamlining chatbot interface operations.
• Tools: Python, Go, Azure DevOps, Docker, Excel, REST API, Flask, SAP BTP, SentenceTransformer, pyttsx3, JIRA, Grafana,

Fraunhofer IIS

• Recommendation System Development: Contributed to advanced recommendation system, improving patient treatment planning precision by 20%.
• Data Analysis Enhancement: Enhanced data analysis capabilities using Python, increasing analytical efficiency by 30%.
• Prediction Accuracy: Improved prediction accuracy and reliability by implementing and fine-tuning a Random Forest Classifier, achieving a 15% boost in model performance.
• Model Transparency: Integrated mlflow for model transparency and reproducibility, ensuring consistent workflow documentation.
• Team Collaboration: Fostered teamwork by establishing a well-maintained GitLab code repository, improving collaboration and code quality by 25%.
• Tools: Python, Random Forest Classifier (Scikit-learn), MLflow, Pandas & NumPy, Matplotlib & Seaborn, Jupyter Notebooks, GitLab

Retorio

• Test Automation Framework Development: Designed and developed test automation frameworks using Puppeteer and Jest, reducing test execution time by 40%.
• CI Integration: Integrated automation frameworks with GitLab CI, enhancing testing efficiency by 35%.
• Bug Identification: Conducted manual testing to identify bugs and issues, improving platform stability by 25%.
• Comprehensive Test Coverage: Scripted test cases in JavaScript, ensuring 95% test coverage.
• Performance Reporting: Reported daily performance metrics to the development team lead, ensuring timely delivery of high-quality scripts.
• Documentation: Documented test procedures and results, facilitating future reference and ensuring reproducibility.
• Tools: JavaScript, Puppeteer, Jest, GitLab, Manual Testing

IBM

• Automation Testing and DevOps: Conducted UI automation testing and DevOps using Puppeteer, JavaScript, and Ansible, reducing manual testing efforts by 60%.
• Automated Test Scripts: Developed automated test scripts using Puppeteer, JavaScript, Jest, Allure, and Python, increasing test coverage by 50%.
• Framework Development: Built a new automation framework for IBM Cloud Pak for Data, improving test efficiency by 45%.
• Test Result Analysis: Analyzed test results daily, improving defect detection rate by 30%.
• Mentoring and Code Reviews: Mentored team members and participated in code reviews, enhancing code quality by 25%.
• Use Case and Specification Development: Developed use cases, user interface specifications, and user requirement documents, ensuring clear and precise project documentation.
• Reporting: Generated reports using Allure framework, improving transparency and communication with stakeholders.
• Agile Participation: Attended daily scrum meetings, actively sharing risks and roadblocks, and ensuring smooth project progress.
• Tools: JavaScript, Python, Bash/Shell Scripting, Puppeteer, Jest, Allure Framework, GitHub, Manual Testing, Ansible, IBM Cloud Pak for Data, Agile Scrum Meetings

Programming Languages

Python

JavaScript

GO

Shell Scripting

Databases

PostgreSQL

MongoDB

SQL

Quantum & Systems Focus

AI, LLMs & Machine Learning

Pandas

NumPy

Matplotlib

Keras

TensorFlow

PyTorch

Scikit-learn

LLM

Agentic AI

Reinforcement Learning

Tools & Testing

Jira

Postman

Puppeteer

Figma

Jest

Ansible

Git

Prometheus

DevOps & Cloud

Docker

Jenkins

Kubernetes

Azure DevOps

Terraform

Cloud Platforms

AWS

Azure

Google Cloud

Technical Documentation

Confluence

LaTeX