About Me
I am a Physics undergraduate at Institut Teknologi Bandung with a concentration in Science Data and Artificial Intelligence and a minor in Entrepreneurship. My work sits at the intersection of applied machine learning, software engineering, and domain-focused product building.
Across research, internships, and institutional systems, I have worked on hydrocarbon zone prediction, facial-recognition inference services, multimodal document analysis, and full-stack education platforms. I prefer work where experimentation, product decisions, and implementation stay closely connected.
Technical Focus
My recent work falls into three areas:
Applied ML Research in well-log interpretation, hydrocarbon zone prediction, class-imbalance handling, and GPU-accelerated model benchmarking at FTTM ITB.
Intelligent Product Workflows across computer vision, multimodal document processing, structured LLM outputs, and feedback loops for improving AI-assisted features.
Full-Stack Platform Engineering for learning, publishing, payments, and community systems, including storage-backed media delivery, subscriptions, content workflows, and role-based access control.
Current Work
I currently divide my time between research, applied ML systems, and product-oriented platform work.
Research & ML Systems
Recent work includes hydrocarbon modeling at FTTM ITB, facial-recognition and inference services at Artajasa, and technical strategy work around Web3 payment and settlement models.
Platforms & Education
Alongside research, I build education and organizational platforms such as PHIWIKI, himafiitb.com, and Kuliah Kit, and teach Python-based analytical workflows in academic settings.
Education & Training
My formal training is in Physics at Institut Teknologi Bandung, combining data analysis, computational methods, and machine learning applications with rigorous statistical reasoning. I also completed a minor in Entrepreneurship to integrate technical development with business strategy.
I graduated from Bangkit Academy's Machine Learning path with a 90.2% final mark. This intensive 463-hour curriculum covered Python automation, data analysis, classical machine learning, TensorFlow, and model deployment.
I value clear problem framing, careful implementation, and measurable results across both research and product work.