Hi, I'm Sharif Ullah
AI Engineer & Researcher building intelligent systems — from LLM-powered products and multi-agent architectures to computer vision and real-time analytics.
AI Engineer & Researcher building intelligent systems — from LLM-powered products and multi-agent architectures to computer vision and real-time analytics.
About Me
I'm a passionate software engineer with 5+ years of experience delivering innovative solutions across AI, ERP, and Fintech. I've built production AI products for multinational agencies, government organizations, and startups across Bangladesh, Japan, Saudi Arabia, and the UK.
My work spans LLM-powered chatbots and RAG systems, computer vision surveillance platforms, emotion detection engines, multi-agent CRM automations, and full-stack SaaS products. I thrive on turning complex problems into scalable, impactful products.
I'm also an active researcher focusing on Autism Spectrum Disorder detection using multimodal deep learning — combining pose estimation, emotion recognition, and audio analysis.
Featured Work
Production AI systems I've designed, developed, and deployed — from emotion-aware campaign analytics to multi-agent CRM automation.
Built VML's flagship AI product that analyzes campaign videos by detecting viewer emotions in real-time. Combines emotion detection models, LLMs, Big Data pipelines, and Google Cloud Platform.
RAG-based AI platform helping doctors analyze medical reports, generate insights, and provide patient support with intelligent document understanding.
Intelligent worksheet generation platform for ESL teachers with AI-powered question and image generation, customized for language learning.
Multi-agent AI system automating end-to-end CRM operations using OpenClaw LLM and orchestrated agents for lead management and workflow automation.
RAG-based chatbot for the hotel industry — users book rooms, inquire about services, and manage reservations through natural language conversation.
RAG-powered chatbot for a government financial organization, assisting with loan inquiries, document guidance, and customer support.
Desktop & web surveillance platform using object detection and pose estimation, optimized for CPU inference with OpenVINO for a London-based startup.
Complete smart hotel management — web platform + two mobile apps automating entire operations from booking to in-room service with AI chatbots.
AI-powered virtual try-on system for fashion brands, enabling customers to visualize clothing using computer vision and generative models.
Real-time production throughput tracking system for a matzoh bakery. YOLOv11 object detection with ByteTrack persistence tracks dough balls through class transition to matzah sheets, assigning per-worker stats via calibrated anchor zones on live CCTV feeds.
Tech Stack
Career
Developing home loan software "eSheba" and mobile applications for this government financial organization. Building FinTech modules with Java JEE, Spring Boot, Oracle Cloud, and Flutter.
Led development of AI CCTV surveillance using object detection and pose estimation. Built desktop and web apps with optimized CPU inference via OpenVINO and YOLOv8.
Developed VML's MVP AI product "Reveal" — emotion-aware campaign analytics. Built ETL pipelines, dashboards, and backend services on GCP. Worked on micro-expression deep learning models.
Developed a comprehensive ERP system for a Japan-based software company.
⭐ Top Performer (FY 2021-22)Built AI applications for Japan Railway — train detection, human activity recognition, rail-crossing surveillance. Developed pose estimation and Bengali OCR using deep learning.
Freelancing
Actively collaborating with international clients as an AI engineer, building custom AI solutions and automation tools.
Intelligent advertising that customizes digital banners based on real-time age and gender detection using YOLOv8 and OpenVINO.
Smart assistant that listens to phone calls, identifies meeting intents, and auto-schedules events in Google Calendar with transcription.
Scalable auto-annotation tool using object detection and pose estimation to label 25,000+ data samples automatically.
Intelligent agents automating customer phone calls, SMS, and emails driven by LLM responses tailored to business content.
Education
Chittagong University of Engineering & Technology (CUET) — one of the premier government engineering universities in Bangladesh.
Research
Focused on multimodal Autism Spectrum Disorder (ASD) detection using pose, emotion, audio, and video analysis.
Focusing on facial expression recognition for children with ASD to improve multimodal behavior analysis.
Using RAG-based models for detecting Autism Spectrum Disorder through pose estimation and emotion data analysis.
Served as subreviewer for ECAI 2025, reviewing papers in AI and machine learning.
Problem Solving
Get in Touch
I'm always open to discussing AI projects, freelance opportunities, research collaborations, or just a good tech conversation.