Cairo, Egypt · Open to remote worldwide

Sara Abdelazim

AI & Data Engineer building production LLM systems and network intelligence for Telecom Egypt's national network.

Master's in Data Science and AI from the University of Ottawa. I build an enterprise knowledge assistant on a local LLM and transformer-based anomaly detection over millions of network logs. These systems cut downtime, configuration errors, and time to root cause.

Sara Abdelazim
Production Systems

AI running inside a national network

Systems I design, build, and run in production in Telecom Egypt's network, as AI & Data Engineer at Alkan Telecom. The code is internal, so each entry documents the architecture, the approach, and the results.

In productionNov 2025 - Present

Enterprise Knowledge Assistant · Local LLM

An enterprise assistant built on a local LLM, serving senior management and cross-domain teams. I designed the system architecture and resource plan, and implemented retrieval across internal documents, databases, and APIs using a Chroma vector store with hybrid retrieval (BM25 + embeddings + reciprocal rank fusion). The assistant replaces manual searches across scattered systems, and every answer stays on local infrastructure.

Local LLMRAGChromaBM25 + Embeddings + RRFSystem Design
In productionMar 2025 - Present

Network Log & Alarm Intelligence · SysLogs

Multi-component ML project for network fault detection and root-cause analysis, processing millions of log messages ingested from Elasticsearch, with coverage scaled from 5 to 12 network devices. The system surfaces faults earlier and shortens the path from alarm to root cause.

  • Log anomaly detection (LogBERT): adapted the open-source LogBERT transformer to telecom log data, developing the full preprocessing pipeline from scratch (Drain3 template parsing into sequential model inputs); introduced PEFT fine-tuning for incremental learning, cutting retraining time on millions of logs.
  • Novel log detection (first-time-seen): flags log messages outside the model's training distribution to identify novel fault types early.
  • Log-alarm association & co-occurrence: predicts expected logs from alarm occurrences and identifies causal log-alarm relationships within time windows.
PyTorchTransformersPEFTDrain3ElasticsearchAnomaly Detection
DeliveredMar - Apr 2026

Router Configuration Standardization · Golden Image

Extracted and consolidated configuration templates from production routers into a standard golden-image configuration applied across devices, reducing configuration errors and outages and cutting setup time for new devices.

Network AutomationConfiguration Analysis
Ongoing

Data Pipelines & Monitoring

Designed and automated ETL and monitoring pipelines with Python, SQL, IBM CP4D, and DataStage, maintaining data integrity across large data volumes. Monitoring catches pipeline issues before they reach the teams that depend on the data.

IBM CP4DDataStageETLSQL
Selected Projects

Open work with code

Machine learning, NLP, and analytics projects, each with source available.

Detecting LLM-Generated Text

NLP system for detecting AI-generated text, delivered as a master's graduation project with Wakeb Data. Fine-tuned BERT and RoBERTa for English, AraBERT for Arabic, and mBERT for multilingual detection.

PyTorchHugging FaceBERTStreamlit

Drug Reviews: NLP Sentiment & Classification

Sentiment analysis and drug-category classification over patient reviews: cleaning, tokenization, NER, and lemmatization, with EDA surfacing top conditions and drugs.

PythonNLPscikit-learn

Clinic No-Show Prediction

SVM and decision-tree models predicting patient no-shows at a medical center to improve appointment scheduling efficiency.

RSVMHealthcare

DDoS Attack Detection

EDA over network traffic plus two classifiers, a tuned LDA baseline and a random forest, for robust DDoS attack detection.

PythonRandom ForestSecurity

Tableau Sales Story

Multi-tab Tableau dashboard analyzing customer demographics, product profitability, and sales trends for Adventure Works Cycles.

TableauData Viz

AdventureWorks Power BI Analysis

Interactive dashboard covering reseller performance, employee sales, and product trends, with drillthrough pages, date filters, and Base64 image handling for in-report visuals.

Power BISQL

SSIS ETL for ITI Data

Automated ETL processes integrating student, course, department, and instructor data with SQL Server Integration Services.

SSISETL

SSAS & MDX Sales Cubes

Built and queried multidimensional cubes with MDX to extract sales insights from cubes and dimensions.

SSASMDX

Fremont Bridge Time Series

Time-series analysis of Seattle bicycle traffic identifying daily, weekly, monthly, and yearly patterns in Python.

PythonTime Series
Experience

Where I've built and taught

Production AI engineering, team leadership, and teaching.

AI & Data Engineer · Alkan Telecom (Client: Telecom Egypt)

Nov 2024 - Present
  • Built and run the enterprise knowledge assistant end to end: architecture, resource plan, and implementation of a local LLM with hybrid retrieval, serving senior management and cross-domain teams.
  • Built SysLogs: transformer-based log anomaly detection, first-time-seen detection, and log-alarm association over millions of Elasticsearch-ingested logs, cutting time to root cause for network teams.
  • Standardized router configurations into a golden image, reducing configuration errors and device setup time.
  • Designed ETL and monitoring pipelines on IBM CP4D and DataStage, maintaining data integrity across large volumes.

Data Analysis Instructor · MEC (part time)

Jan - Mar 2025
  • Taught Python and Excel through applied business cases in data cleaning, reporting, and analysis, designed for participants from non-technical backgrounds.

Coding Instructor · iSchool (part time)

Jun - Sep 2024
  • Delivered coding sessions and workshops covering data science fundamentals and application development for the DEMI program.

AI Engineer, Internship · Wakeb Data

Oct 2023 - Feb 2024
  • Led the team that built an NLP system to detect LLM-generated text, delivered as a master's graduation project.
  • Fine-tuned transformer LLMs with PyTorch: BERT and RoBERTa (English), AraBERT (Arabic), mBERT (multilingual).
Skills

Tools I work with

Used in production systems and analysis work.

GenAI / LLM

RAGVector DBs (Chroma)Hybrid Retrieval (BM25 + Embeddings + RRF)PEFT Fine-tuningHugging FaceMCP

Data Science & ML

PyTorchscikit-learnPandasNumPyTensorFlowKerasStreamlit

Data Engineering

SQLETLElasticsearchIBM CP4DDataStageWatson StudioPySparkMongoDBData Warehousing

BI & Visualization

Power BITableauExcelMSBI (SSIS · SSRS · SSAS)

Programming

PythonRC#
Education & Certifications

Foundation and continued learning

Formal degrees alongside ongoing certification work.

Professional Master's in Computer Engineering: Data Science & AI

University of Ottawa (uOttawa)
2023 - 2024

Intensive Code Camp: Business Intelligence

Information Technology Institute (ITI)
2022 - 2023

Bachelor's in Computer Science & AI: Medical Informatics

Beni Suef University (BSU)
2018 - 2022

Certifications

  • Transformer Architecture & Attention Mechanisms, Self-study2026
  • Model Context Protocol (MCP), Self-study2026
  • Market Basket Analysis in Python, DataCamp2025
  • Introduction to AWS, DataCamp2024
  • Introduction to PySpark, DataCamp2024
  • Natural Language Processing in Python, DataCamp2023
  • AI Analyst, IBM2023
  • Predictive Analysis, IBM2023
  • Big Data, IBM2023