Headline

Data Scientist | Python, ML, NLP, RAG & Agentic AI

About

Senior AI/Data Scientist with experience designing and deploying production AI systems across healthcare and e-commerce domains. Specialized in NLP, Retrieval-Augmented Generation (RAG), LLM applications, semantic search, recommendation systems, and machine learning solutions that solve real business problems. Experienced in building end-to-end AI products, including hybrid retrieval systems, AI agents, multilingual content generation pipelines, predictive models, and computer vision applications. Strong background in taking solutions from data modeling and experimentation to production deployment, observability, evaluation, latency optimization, and continuous improvement. Passionate about building scalable, reliable, and measurable AI systems with a focus on business impact, production quality, and user experience. Open to international opportunities and relocation.

Location

Tehran Province

AI stack

claude code

cursor

gemini

hugging face

langchain

langgraph

Work experience

Senior Artificial Intelligence Engineer at PassargadWeb, Jun 2026 - Present · 5 mos, Isfahan Province, Iran

Senior Artificial Intelligence Engineer at GolestanEC, Sep 2023 - May 2026 · 2 yrs 9 mos, Tehran Province, Iran, Built and deployed AI-driven e-commerce systems including RAG pipelines, NL2SQL agents, semantic search, recommendation models, multimodal generation, and LLM-powered content automation using LangChain, FAISS, PostgreSQL, and Gemini APIs. Applied machine learning, NLP, and deep learning techniques (ParsBERT, Bi-LSTM, GRU, embeddings) to customer analytics, CRM intelligence, sales optimization, and Persian-language product understanding at production scale.

Data Scientist at Modiseh.com, Sep 2021 - Sep 2023 · 2 yrs 1 mo, Tehran, Developed machine learning and analytics solutions for customer segmentation, churn prediction, CLV forecasting, recommendation optimization, and marketing intelligence, driving measurable improvements in sales, retention, and campaign performance. Built scalable data processing and enrichment pipelines using Python, SQL, and OpenCV, alongside dashboards and visualization systems to support business intelligence and operational automation.

Research Assistant | Healthcare AI & Clinical NLP at DKR@IUT, Oct 2019 - Apr 2021 · 1 yr 7 mos, Isfahan, • Collaborated with AI research teams on Healthcare AI systems with a focus on Clinical NLP applications and medical text understanding. • Conducted research in Natural Language Processing (NLP) and Deep Learning, focusing on clinical text classification, sentiment analysis, named entity recognition (NER), and ontology-based information extraction. • Designed and implemented deep learning architectures including RNNs, CNNs, and Transformer-based models for healthcare and NLP-related tasks. • Collected, cleaned, and preprocessed large-scale clinical and textual datasets for research and experimentation. • Performed literature reviews and evaluated state-of-the-art research in Clinical NLP and Deep Learning to support model development. • Developed data preprocessing pipelines and model training workflows using Python, TensorFlow, Keras, and Scikit-learn. • Improved model performance through feature engineering, hyperparameter tuning, and optimization techniques.

Education

Master's degree, Computer Software Engineering, Isfahan University of Technology

Bachelor's Degree, Computer Software Engineering, Kharazmi University

Public links

github: https://github.com/saharkhalafi