Mr
- Verfügbarkeit einsehen
- 0 Referenzen
- auf Anfrage
- 12627 Berlin
- Europa
- ur | en | de
- 09.08.2026
Kurzvorstellung
Geschäftsdaten
Qualifikationen
Projekt‐ & Berufserfahrung
7/2025 – 4/2026
TätigkeitsbeschreibungAcademic Research Contributor in Health Sector (Volunteer)
Eingesetzte QualifikationenSoftwareentwickler, Software Architecture, Machine Learning
3/2024 – 7/2025
TätigkeitsbeschreibungDeveloped a YOLOv8-based computer vision system for real-time cone, boundary, and trajectory detection for autonomous racing applications.
Eingesetzte QualifikationenMachine Learning Engineer
10/2022 – 2/2026
Tätigkeitsbeschreibung
Virtual Platform Integration (vOffice)
• Bridged AI backends with vOffice interfaces using Node.js and Next.js for real-time AI avatar data flow.
• Developed specialized AI agents: AI Tilda (Translation), AI Peter (Legal), and AI Mary (General Assistant).
• Integrated Whisper AI, WebRTC, and Simli for low-latency, lip-synced AI avatars in virtual conferences.
Legal AI Engineering & Research
• Built a privacy-first legal AI platform using local LLMs and custom BERT-based NER models for GDPR-compliant document anonymization.
• Engineered a modular on-device AI deployment architecture using Turbo.net and native macOS packaging.
• Designed and implemented privacy-first legal RAG systems using OpenWebUI, Ollama, FAISS, and Qdrant for semantic retrieval over 8GB+ German legal datasets.
• Developed prompt-based local LLM pipelines using Ollama to extract structured legal information into JSON key-value pairs.
• Implemented contextual retrieval chunking, metadata filtering, semantic search, and class-based indexing strategies to improve retrieval precision and reduce hallucinations.
• Developed custom OpenWebUI tool scripts to dynamically retrieve context from Qdrant because direct custom RAG integration was unavailable in the free OpenWebUI environment.
• Designed prompt engineering and context engineering workflows including legal grounding prompts, structured extraction prompts, and hallucination reduction strategies.
• Created a Scikit-learn document classification system for automated legal email filing workflows.
• Fine-tuned German LLMs (LeoLM and Llama 3.2) using PEFT, LoRA, and quantization techniques.
Legacy Modernization & Tooling
• Built a specialized C# code converter to automate migration of legacy VB/VBA systems to modern .NET architectures.
• Developed Outlook add-ins using MAUI and Blazor to extend legal software functionality.
Generative KI, Machine Learning Engineer, Softwareentwicklung (allg.)
1/2019 – 9/2019
Tätigkeitsbeschreibung
Software Engineer | Euronet Worldwide – Karachi, Pakistan | Jan 2019 – Sep 2019
• Engineered secure backend banking modules using ASP.NET MVC and C# for high-volume financial transactions.
• Developed fraud detection and prevention mechanisms for banking applications.
• Managed complex MS SQL environments using stored procedures and triggers.
• Supported live monitoring and reporting tools for ATM and POS networks with 24/7 availability requirements.
Software engineering / -technik
10/2017 – 1/2019
Tätigkeitsbeschreibung
Software Engineer | SalTec Powerlink – Karachi, Pakistan |Oct 2017 – Jan 2019
• Developed WPF-based industrial configuration software for WIFI, Ethernet, and industrial hardware modules.
• Implemented REST/RPC protocols for remote device management.
• Refactored real-time telemetry systems for Grid, Genset, and UPS power infrastructure.
• Led migration to high-performance database structures using Data Flow Diagrams.
• Collaborated in Agile teams to identify bugs and create test cases for financial applications using JIRA.
Software engineering / -technik
Zertifikate
Über mich
PROFESSIONAL SUMMARY
AI/ML & Software Engineer specialized in privacy-first intelligent systems, Generative AI, Agentic AI workflows, and German Legal Tech solutions. Experienced in architecting high-performance Retrieval-Augmented Generation (RAG) systems using local LLMs, vector databases, contextual retrieval, prompt engineering, and tool-based AI workflows. Expert in developing custom BERT-based NER models for GDPR-compliant document anonymization and deploying privacy-first AI solutions on-premises. Proven track record leading end-to-end AI integrations—from real-time AI avatars using Whisper AI and WebRTC to local LLM deployment, knowledge retrieval systems, and enterprise software modernization.
CORE COMPETENCIES
Generative AI (GenAI), Agentic AI, LLM Engineering, Retrieval-Augmented Generation (RAG), Prompt Engineering, Context Engineering, Local LLM Deployment, NLP & NER, Computer Vision, AI System Design, Privacy-First AI, Backend Engineering, Vector Databases, AI Evaluation & LLMOps.
Weitere Kenntnisse
Programming Languages
Python C# JavaScript TypeScript Java
AI & Machine Learning
OpenAI HuggingFace LangChain LangGraph LlamaIndex
RAG & Vector Databases
Qdrant FAISS
Backend
FastAPI Flask ASP.NET NodeJS
Frontend
React NextJS Flutter
DevOps & Tools
Docker GitHub Actions Linux
? About Me
? Building AI-powered applications using LLMs and Agentic AI
? Developing RAG systems with Vector Databases
? Working with NLP, NER, and Information Retrieval
⚡ Creating scalable backend systems with Python and .NET
? Based in Berlin, Germany
? Continuously learning advanced AI architectures and cloud technologies.
? Areas of Interest
Generative AI
Agentic AI
Multi-Agent Systems
Retrieval-Augmented Generation (RAG)
AI Automation
NLP & NER
Fine-Tuning LLMs
AI Infrastructure
MLOps
? Featured Projects
?️ Legal AI Assistant
Privacy-first AI assistant for legal professionals using local LLMs, RAG pipelines, and custom NER models.
? GDPR Document Anonymizer
Custom BERT-based Named Entity Recognition system for anonymizing legal documents and protecting sensitive information.
? Advanced RAG Platform
High-performance Retrieval-Augmented Generation system using Qdrant, FAISS, and domain-specific indexing strategies.
?️ AI Avatar Platform
Real-time AI avatars powered by Whisper, WebRTC, and conversational AI technologies.
?️ Formula Student AI
YOLOv8-based computer vision system for autonomous racing car navigation and track detection.
? License Plate Recognition
YOLOv5-based Automatic License Plate Recognition (ALPR) system deployed in commercial environments.
Persönliche Daten
- Urdu (Muttersprache)
- Englisch (Fließend)
- Deutsch (Gut)
- Europäische Union
Kontaktdaten
Nur registrierte PREMIUM-Mitglieder von freelance.de können Kontaktdaten einsehen.
Jetzt Mitglied werden