11/11/2026 updated
Premium member
100 % availableBackend & AI Engineer | Python, Django & LLM/RAG Systems
Fyresdal, Norway
Worldwide
Full Stack Web Development, Holberton School (2019-2021)About me
I am a backend and AI engineer with 4+ years of experience building production systems with Python, Django, FastAPI, Node.js, PostgreSQL and cloud services.
DevOpsDjangoMiddlewarePython (Programming Language)PostgreSQLSAP ABAPFlaskPrompt EngineeringSAP BTPBackendFastAPISAP FioripandasBackend ProgrammingCelery
AI & LLM Engineering
Expertise in OpenAI API (GPT-4, reasoning models, structured output parsing), LangChain, and end-to-end RAG pipeline design covering ingestion, chunking, embedding, retrieval, and generation. Proficiency in hybrid retrieval combining vector and keyword/BM25 search, metadata filtering, dynamic LLM routing by confidence score, prompt engineering and versioning, as well as vector stores such as Qdrant, pgVector, and MongoDB for large-scale corpus processing (300+ books, 1.8M+ pages).
Python & Backend Development
Strong command of Python 3.12+, OOP, and clean architecture principles. Hands-on experience with Django, Django REST Framework (DRF), FastAPI, Flask, Django ORM, custom plugins and middleware, Celery, RabbitMQ, event-driven workflows, parallel extraction engines, CLI scripting (argparse, Bash), and REST API design and versioning.
DevOps & Cloud
Practical experience with Docker, Docker Compose, AWS, GCP (Cloud Run, App Engine), Azure (Active Directory), Jenkins CI/CD, YAML-driven configuration, Linux, Bash, Git, and Cloudflare. Proven track record deploying and versioning full production pipelines across multiple cloud environments.
Document Processing
Proficiency in PyMuPDF (fitz) and Tesseract OCR (pytesseract) for text extraction from large document corpora. Experience with section-aware chunking and normalization pipelines for structured data preparation.
Databases
Broad experience with PostgreSQL, MySQL, MongoDB, Neo4j, PLSQL, and Oracle 12c/19c. Skilled in data modeling, query optimization, and managing data lifecycle across relational and NoSQL systems.
Data & Reporting
Hands-on use of pandas, NumPy, and openpyxl for data processing, trend analysis, and JSON-to-Excel report generation. Experience building Streamlit dashboards and Metabase integrations, as well as designing batch processing and data pipeline workflows.
Frontend & JavaScript
Working knowledge of JavaScript, React, Node.js, Vue.js, Nuxt.js (versions 2 and 3), and Tailwind CSS for building interactive frontends and dashboards.
Testing & Quality
Experience with Pytest, Django UnitTests, and unit and integration testing for services and pipelines. Familiarity with CodeceptJS and SonarQube for code quality assurance.
Expertise in OpenAI API (GPT-4, reasoning models, structured output parsing), LangChain, and end-to-end RAG pipeline design covering ingestion, chunking, embedding, retrieval, and generation. Proficiency in hybrid retrieval combining vector and keyword/BM25 search, metadata filtering, dynamic LLM routing by confidence score, prompt engineering and versioning, as well as vector stores such as Qdrant, pgVector, and MongoDB for large-scale corpus processing (300+ books, 1.8M+ pages).
Python & Backend Development
Strong command of Python 3.12+, OOP, and clean architecture principles. Hands-on experience with Django, Django REST Framework (DRF), FastAPI, Flask, Django ORM, custom plugins and middleware, Celery, RabbitMQ, event-driven workflows, parallel extraction engines, CLI scripting (argparse, Bash), and REST API design and versioning.
DevOps & Cloud
Practical experience with Docker, Docker Compose, AWS, GCP (Cloud Run, App Engine), Azure (Active Directory), Jenkins CI/CD, YAML-driven configuration, Linux, Bash, Git, and Cloudflare. Proven track record deploying and versioning full production pipelines across multiple cloud environments.
Document Processing
Proficiency in PyMuPDF (fitz) and Tesseract OCR (pytesseract) for text extraction from large document corpora. Experience with section-aware chunking and normalization pipelines for structured data preparation.
Databases
Broad experience with PostgreSQL, MySQL, MongoDB, Neo4j, PLSQL, and Oracle 12c/19c. Skilled in data modeling, query optimization, and managing data lifecycle across relational and NoSQL systems.
Data & Reporting
Hands-on use of pandas, NumPy, and openpyxl for data processing, trend analysis, and JSON-to-Excel report generation. Experience building Streamlit dashboards and Metabase integrations, as well as designing batch processing and data pipeline workflows.
Frontend & JavaScript
Working knowledge of JavaScript, React, Node.js, Vue.js, Nuxt.js (versions 2 and 3), and Tailwind CSS for building interactive frontends and dashboards.
Testing & Quality
Experience with Pytest, Django UnitTests, and unit and integration testing for services and pipelines. Familiarity with CodeceptJS and SonarQube for code quality assurance.
Experience
Professional experience0 - 5 years
Freelancer since2022
Languages
ArabicNative speakerEnglishNative speakerFrenchFluentNorwegianGood
Project history
Designed and implemented a full end-to-end RAG pipeline powering an AI assistant embedded in an enterprise monitoring platform, processing approximately 1.8 million documentation pages and 300+ technical books. Built hybrid retrieval combining pgVector cosine similarity search with PostgreSQL full-text keyword search and metadata filtering. Implemented a confidence-based LLM routing layer for dynamic model selection. Architected a real-time monitoring platform aggregating operational telemetry across 8 production systems and 13 data sources. Designed a parallelism-based Python extraction engine and built data aggregation and reporting pipelines using pandas and NumPy. Developed Streamlit dashboards and a React frontend with Azure Active Directory integration.
Led the full technical architecture and infrastructure strategy for a creator-brand collaboration platform. Designed and implemented a multi-stage CI/CD pipeline using Jenkins. Architected the deployment strategy using GCP with dedicated Supabase databases per environment. Built a complete observability stack using OpenReplay and SigNoz. Developed and orchestrated data pipelines for social media intelligence and implemented a resilient backup and disaster recovery system.
Integrated the OpenAI API (ChatGPT) into a learning platform for AI-powered assistance for teachers and students. Designed and implemented a subscription management platform for Africa's largest telecom company with Moodle integration, mobile money payment systems, and USSD/SMS support. Implemented Celery with RabbitMQ for asynchronous event-driven background processing. Developed a custom Moodle plugin and built a Django-powered analytics platform aggregating student engagement data.