Ismum User
@ismumuser
I build production computer vision and AI systems from data to deployment.
What I'm looking for
At The Data Island, I built YOLO-based retail product detection for Unilever Bangladesh, curating 200,000+ shelf images across 160 categories and achieving 98% mAP@50. I also contributed to a 97% accurate planogram compliance solution, faster annotation workflows, structured logging, and Redis caching.
I've built end-to-end AI systems spanning facial recognition with RetinaFace, AdaFace, and FAISS, LiDAR point-cloud segmentation, healthcare assistants, and RAG-based educational tools. My usual toolkit includes Python, PyTorch, FastAPI, LangChain, CUDA, and Docker—from data curation and model training through deployment.
Experience
Work history, roles, and key accomplishments
Computer Vision Engineer
The Data Island
Nov 2025 - Apr 2026 (5 months)
Developed retail product detection models using YOLO variants for automated shelf analysis and inventory monitoring. Built a semi-automated annotation pipeline reducing manual labeling time by 80% and contributed to a planogram compliance solution.
Education
Degrees, certifications, and relevant coursework
North South University
Bachelor of Science, Computer Science and Engineering
2022 -
Pursuing a Bachelor of Science in Computer Science and Engineering.
Availability
Location
Authorized to work in
Website
ismum.vercel.appJob categories
Skills
Interested in hiring Ismum?
You can contact Ismum and 90k+ other talented remote workers on Himalayas.
Message IsmumGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
