AI Engineer
egeroo.ai
Improving retrieval, provider integrations and evaluation for production conversational AI.
Delivered7.22s → 1.1s intent-query latency; MLflow tracing across RAG and agentic flows.
Production systems. Faster responses. Lower costs.
From the model to the person using it.
egeroo.ai
Improving retrieval, provider integrations and evaluation for production conversational AI.
Delivered7.22s → 1.1s intent-query latency; MLflow tracing across RAG and agentic flows.
egeroo.ai
Built RAG Q&A, order-taking, recommendation and multimodal agents for conversational products.
DeliveredLowered AI operating cost by about 85% and shipped four chatbot architectures.
Production improvements across cost, latency, and product iteration.
Tools follow the problem.
Analyzed customer data and compared classification models, delivering a notebook, model artifacts and a written report.
Built a character-level GPT from scratch using PyTorch, implementing attention, training and Indonesian poetry generation.
A conversational RAG guide that answers questions across Hans’s projects, experience and source material.
Courses, certificates, and time spent getting better.
Extended DynaMMo with class-balanced focal loss to help a model learn new eye-disease classes from imbalanced images.
10 RFMiD classes · 5 incremental tasks · 25-sample memory buffer.
Procedia Computer Science 269 · pp. 649–658
Bachelor of Computer Science
BINUS University
Jakarta / Tangerang, Indonesia