RESEARCH • ENGINEERING • SYSTEMS

SAEED
SAFAEI

AI Researcher & Engineer

Building intelligent systems at the intersection of Large Language Models, RAG, Graph Learning, IoT and Robotics.

Based in Tehran, Iran/MSc student in AI & Robotics at Amirkabir University of Technology
PROFILE / 01
Portrait of Saeed Safaei
SAEED SAFAEIAI / SYSTEMS
RESEARCH AREASLLM · RAG · GNN
CURRENT DEGREEMSc AI & Robotics
BSc GPA18.47 / 20
LOCATIONTehran, IR

01 / PROFILE

About Me

An AI engineer and machine-learning researcher working across language models, intelligent devices and physical systems.

I design and develop intelligent systems with a focus on Large Language Models, Retrieval-Augmented Generation, Agentic AI, natural language processing, deep learning and intelligent robotics — taking research ideas from R&D to usable products.

My work also includes technical team leadership, interdisciplinary project management, PEFT-based fine-tuning of generative models, and the design of multi-agent AI architectures.

Technical focusLLM / RAG / GNN / Robotics
EducationMSc AI & Robotics · Amirkabir University of Technology
AvailabilityResearch & engineering collaboration

02 / DIRECTIONS

Research Interests

Questions and systems I am currently studying and building.

01

Large Language Models

LLM-based intelligent systems, language understanding and PEFT fine-tuning.

↗
02

Retrieval-Augmented Generation

Reliable, knowledge-grounded AI systems with semantic retrieval and evaluation.

↗
03

Graph RAG

Graph-augmented retrieval architectures for stronger reasoning in language models.

↗
04

Graph Neural Networks

Learning representations from graph-structured data.

↗
05

LLM + Graph Learning

Combining language models with GNNs to improve graph learning.

↗
06

Intelligent Devices

IoT, industrial intelligence and autonomous robotic systems.

↗

03 / SELECTED WORK

Featured Projects

Selected AI, robotics and embedded systems from research, product development and academic work.

LLM / PEFT

AI / LLM

LLM Fine-tuning

Designed PEFT fine-tuning for Gemma-family models using LoRA and adapters, with evaluation of catastrophic forgetting and optimization for Persian and domain-specific use.

GemmaLoRAPEFT
TRANSFORMER

AI / DEEP LEARNING

Mini Transformer from Scratch

Implemented a full Transformer in PyTorch, including self-attention, multi-head attention, positional encoding and feed-forward layers, applied to sentiment analysis.

PyTorchAttentionNLP
LIDAR / EKF

ROBOTICS / PERCEPTION

Robot Localization & Motion Estimation

Developed LiDAR processing, ICP scan matching and an Extended Kalman Filter for localization of autonomous robots.

LiDARICPEKF
Filament Dryer Pro monitoring interfaceView project ↗

IOT / EMBEDDED

Filament Dryer Pro

A connected filament drying system with temperature, humidity and wireless control considerations.

IoTEmbeddedControl
RFID smart access control deviceView project ↗

IOT / SECURITY

RFID Smart Access

An RFID access device with a web application for user and permission management.

RFIDWeb AppIoT
Strimiko game AI optimization projectView project ↗

AI / ALGORITHMS

Strimiko Game Optimization

A course project using heuristic algorithms to reduce the execution time of a logic game solver.

AIHeuristicsAlgorithms

04 / TOOLKIT

Technical Stack

Grouped by the kind of system being built.

AI & Machine Learning

PythonPyTorchTensorFlowScikit-learnHugging Face

LLM / NLP

LLMRAGAgentsLangChainLangGraphFAISSPEFT / LoRA

Graph Learning

GNNGraph RAGKnowledge Graphs

Embedded / Robotics

ArduinoLiDARICPEKFIoTGit / GitLab

05 / PATH

Experience & Education

Education, research leadership and product development drawn from the current CV.

2025 — NOW

MSc in AI & Robotics

Amirkabir University of Technology · Tehran Polytechnic

Master’s student in Computer Engineering — Artificial Intelligence and Robotics, admitted as a distinguished talent student.

3+ YEARS

Head of Research Center

Shahid Nazm Bojnourdi Research Center

Directed research and technology activities for more than three years, including research teams, resource planning and scientific collaboration.

2024 — NOW

Robotics & AI Development Lead

OCS intelligent dental-training robot

Led interdisciplinary computer and electrical teams from R&D to an operational prototype, including technical architecture and task allocation.

2025

AI Bootcamp Instructor

First specialized AI bootcamp in North Khorasan

Designed the curriculum, taught AI and machine-learning concepts, and managed the training program.

2022 — 2025

BSc in Computer Engineering — Software

University of Bojnord

Graduated with distinction in six semesters with a GPA of 18.47 / 20, ranking first in the Computer Engineering cohort.

06 / RECOGNITION

Achievements & Awards

Selected academic, research and competition records from the current CV.

2025

Distinguished talent MSc admission

Amirkabir University of Technology

2022 — 2025

BSc with distinction in 6 semesters

GPA 18.47 / 20 · University of Bojnord

2018 — 2019

Khwarazmi Youth Festival

Provincial awardee

2021

Science and Technology Jihadists

North Khorasan selection

2025

AI course · National Elites Foundation

Specialized artificial intelligence program

2024 — 2025

Applied Project Management

Sharif University of Technology

07 / RESEARCH OUTPUT

Research & Publications

Documented research output and work currently under review.

Download research PDF ↓
DOCUMENT

Internet of Things: A Revolution in the Connected World

Research document, 2024, available in the project archive.

↓
UNDER REVIEW

Occlusion Chutterbox: An Origami-Inspired Robotic Device for Enhancing Dental Occlusion Training

Paper and patent for the OCS educational robot are currently under review.

—
IN PROGRESS

LLM + Graph Neural Networks / Graph RAG

Ongoing research on combining language models with GNNs and Graph RAG architectures for improved reasoning.

—

08 / CV

Curriculum Vitae

View the current CV for education, research, projects and professional experience.

09 / CONNECT

Let's Work Together

Interested in AI, intelligent systems, research collaboration or engineering projects? Feel free to get in touch.

The form uses the preserved PHP mail endpoint when hosted with PHP.