Rizky Putranto

📍 Yogyakarta, Indonesia

Hi, I’m Rizky Agung Dwi Putranto — a Machine Learning Engineer / Data Scientist passionate about designing scalable automation systems, multilingual NLP, and multimodal models that bridge research and production.

I’ve worked at ByteDance and Tokopedia, where I built and optimized large-scale machine learning pipelines for product categorization, attribute extraction, and content safety, impacting millions of users and driving measurable business outcomes.

I’m especially interested in:

Large Language Models (LLMs) and Vision-Language Models (VLMs)
Retrieval-Augmented Generation (RAG) systems
Active learning and data-centric AI
Scalable ML infrastructure and automation

news

Feb 01, 2024	Starting a new position as Algorithm Engineer at ByteDance! 🎉
Jul 22, 2019	Graduated from Universitas Gadjah Mada majoring in Computer Science.
Jul 15, 2019	Starting a new position as Data Scientist at Tokopedia! 🎉

latest posts

Aug 19, 2021	Demystifying Visual Transformer (ViT)

selected publications

Automated Active Learning for Large Scale Ecommerce Product Categorization

Rizky Agung Dwi Putranto, Santosh Yadaw, Diamond Ravi, and 3 more authors

2023

IP.com Technical Disclosure

Abs

Large ecommerce marketplaces, such as Tokopedia, have hundreds of millions of products listed and uploaded frequently by millions of merchants. Therefore it is essential to create reliable categorisation engines that are as automated as possible, scale to millions of listings, and attain a high classification accuracy. Several issues like taxonomy changes, poor data quality, class imbalances and data drift issues cause drops in model performance. Frequent data labelling and model training activities are required to maintain model accuracy. Active learning can be employed to optimise the data labelling activities. This paper discusses the implementation of a novel automated active learning loop that can monitor model performance, use active learning for data collection, integrate with data labelling tools and trigger model re-trainings that can improve productivity by multi-folds.
Alignment Based Siamese Network Model For Face Verification

Rizky Agung Dwi Putranto and Wahyono

In , 2019