AI Engineer with 1+ years in LLM-powered RAG applications & Data Analytics
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Results-driven Data Engineer and Analyst with a proven track record of building production-grade AI and data systems end-to-end—from automated ELT pipelines and modern data stack architectures (Airflow, dbt) to LLM-powered RAG applications deployed at scale. Proficient in Python, SQL (PostgreSQL, MySQL), Power BI, and FastAPI, with demonstrated impact including a 38% improvement in retrieval precision and ~60% reduction in hallucination rates in deployed NLP systems. Brings strong analytical depth across churn prediction modelling, RFM segmentation, and CLV analytics, translating raw data into executive-facing insights and retention strategies. M.Sc. candidate in Information Technology Management (E-Business), combining engineering rigour with business-oriented decision-making.
Shahid Beheshti University
M.Sc. · Information Technology Management (E-Business)
August 1, 2024 – Present
Shiraz University
B.Sc. · Business Management
August 1, 2019 – June 30, 2023
Barman Oloum Gostar (Barmana)
AI Developer
February 1, 2026 – Present
Isfahan, Isfahan Province, Iran
Mobin Afagh Pars (MAPCO)
Marketing & Sales Analyst
March 1, 2022 – March 1, 2023
Shiraz, Fars Province, Iran
Olist E-Commerce: Churn Prediction, CLV & RFM Analytics
January 1, 2026 – January 1, 2026
Delivered an end-to-end customer analytics solution on 100K+ real Olist e-commerce orders spanning 9 relational tables (2016-2018), from raw ETL ingestion to executive-facing Power BI dashboards. Engineered a Python ETL pipeline extracting, cleaning, and standardising nine source tables, loading transformed data into PostgreSQL via SQLAlchemy with parameterised scripts for fully reproducible data loading. Built an RFM segmentation framework classifying customers into behavioural cohorts (Champions, At-Risk, Lost, and others), quantifying revenue at risk per segment and surfacing retention priorities for business stakeholders. Developed a Logistic Regression churn classifier (Precision: 0.80, Recall: 1.00) trained on engineered behavioural and transactional features, generating customer-level churn probability scores to support targeted retention campaigns. Computed Customer Lifetime Value (CLV) metrics at the individual customer level, enabling direct comparison of predicted revenue contribution against churn risk scores to prioritise high-value retention interventions. Designed four interactive Power BI dashboards (Executive Overview, Churn Analysis, RFM Segmentation, CLV Analysis) with DAX measures and cross-filtered pages for self-service business reporting.
View ProjectOlist Modern Data Stack Pipeline
January 1, 2026 – January 1, 2026
Architected and deployed a production-grade, end-to-end ELT pipeline on the Olist dataset, automating data orchestration from raw ingestion through analytics-ready mart delivery via Apache Airflow DAGs and dbt transformations. Engineered a modular dbt project with discrete staging and mart layers, applying source freshness checks and schema tests (not_null, unique, accepted_values) to enforce data quality contracts across all transformed models before downstream consumption. Implemented data quality testing across the full transformation layer, catching schema violations and null constraints at the model level — eliminating silent data errors that would otherwise propagate to dashboards and ML features. Containerised the full stack (Airflow, dbt, PostgreSQL) with Docker Compose, enabling single-command environment reproducibility and eliminating configuration drift across development and deployment contexts.
View ProjectE-Commerce Customer Behaviour Dataset (Open Source)
November 1, 2025 – November 1, 2025
Developed and published an open-source e-commerce dataset capturing demographics, purchasing patterns, device usage, and satisfaction metrics — designed for data analysis, machine learning, and educational use.
View ProjectEducational Space Capacity Gap Analysis (SISP)
May 1, 2025 – June 1, 2025
Applied time series forecasting and predictive modelling (regression and clustering) to identify educational infrastructure capacity gaps, producing a strategic data report to inform Information Systems Planning decisions.
Human Capital Index Impact on E-Government Development
December 1, 2024 – December 1, 2024
Conducted cross-country OLS regression, correlation analysis, and K-Means clustering on a multi-country dataset to quantify the influence of human capital on e-government adoption indices.
Bitcoin Price Analysis: Market Cap, Volume & On-Chain Drivers
November 1, 2024 – November 1, 2024
Applied regression modelling, clustering, and data visualisation to a real-world BTC dataset, quantifying the influence of market cap, trading volume, and on-chain transactions on Bitcoin price and segmenting market conditions into interpretable behavioural regimes.
Machine Learning in Python
365DataScience
January 1, 2025 – Present
Intermediate SQL
DataCamp
January 1, 2025 – Present
Introduction to Power BI
DataCamp
January 1, 2025 – Present
Python Programming
Maktabkhooneh
January 1, 2025 – Present
Cultural Fit Analysis
The candidate's project portfolio shows a blend of personal and academic initiatives, indicating self-motivation and a continuous learning mindset. Their experience as an 'AI Developer' aligns well with an 'AI Engineer' target role, demonstrating direct relevance. The breadth of skills across data engineering, AI/ML, and analytics suggests adaptability and a willingness to tackle diverse technical challenges. The academic background in Information Technology Management (E-Business) also indicates an understanding of business context alongside technical skills.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through their project work, particularly in optimizing retrieval precision and reducing hallucination rates in RAG systems. Their experience in designing modular APIs and containerizing applications suggests an understanding of maintainability and reproducible deployments. The detailed descriptions of their work imply a structured approach to project execution and an ability to translate technical work into business impact.