I build systems where software, data, and AI meet.
Informatics at ITB. Open-source contributor. Distributed systems junkie.
Not the features they use. But the moments when they hesitate.
Movement as a shared language.
Crowds behave like software. Many intentions. One shared space.
I started watching before I started building.
I started with questions about clarity.
Patterns repeat when the environment stays the same.
Code became a way to care. For users I may never meet. For teammates I may never see.
Empathy, without performance.
Silence is sometimes the most respectful interface.
When something is clear, people feel more confident using it.
Less friction. Less asking. More moving forward.
The interface should not be the obstacle.
Inputs. Transitions. Outcomes. And the space between them.
Good work is often just well-managed transitions.
Engineering, to me, is less about solutions and more about transitions.
I prefer systems that feel invisible.
Something that doesn't ask for attention — but earns it over time.
A calm interface is a form of respect.
Carefully. With intention. So others can move without thinking about the system beneath them.
No conclusion. Just continuity.
Institut Teknologi Bandung
BS in Computer Science
2023 - 2027 · Bandung, Indonesia
[International] 2nd Place - Data Analysis Competition 2025
HIMASTA ITS · 2025
[National] Finalist - BRIN AIDeaNation 2025
BRIN · 2025
[National] Finalist - Data Mining GEMASTIK XVIII
Kemdiktisaintek · 2025
[International] Most Outstanding Student Award
Matsuo-Iwasawa Lab, University of Tokyo · 2025
[National] Bakti BCA Scholarship Awardee
PT Bank Central Asia Tbk. · 2025
[National] Honorable Mention - Data Analytics Dash COMPFEST 16
COMPFEST 16 · 2024
[National] 5th Place - Objective Quest Airnology 3.0
BEM FTMM Universitas Airlangga · 2024
[National] 4th Place - Data Analytics FIND IT! 2024
DTETI Universitas Gadjah Mada · 2024
[National] 3rd Place - DATA SLAYER 1.0
HMSD IT Telkom Purwokerto · 2024
[National] 1st Place - DINAMIK 17 Competitive Programming Contest
FPMIPA Universitas Pendidikan Indonesia · 2022
Projects prove I can build. They turn ideas into working systems. Each one solved a problem or answered a question.
Web platform for HMIF's Competition & Community division. Built with Next.js to help association members track achievements and stay motivated. Initiative to increase member participation in competitions and community events.
Next.js · React · TypeScript · Tailwind CSS
Interactive Tableau dashboard analyzing the impact of social media on education in Indonesia. Built custom web scraping pipeline and reached final round of COMPFEST 16 among nationwide participants.
Tableau · Python · Selenium · BeautifulSoup
Full-stack sign language learning platform with real-time hand gesture recognition. Built using computer vision and machine learning for preprocessing and model training with React frontend.
React · Python · OpenCV · MediaPipe
Machine learning model for ONNX runtime that predicts corrosion rates for 9 materials in sulfidic/naphthenic acid conditions. Achieved exceptional RMSE of 0.3 with high predictive accuracy.
Python · ONNX · Machine Learning · Scikit-learn
Built a 32-bit OS kernel with memory paging, round-robin scheduling, hardware drivers (keyboard, VGA 13h, disk), and an EXT2 filesystem. Designed system calls and a user-space shell with core utilities.
Operating Systems · C · Paging · Scheduling
A mini DBMS to learn core internals. Includes a storage engine, buffer/page management, query execution, a simple optimizer, indexing, transactions, and a client-server interface.
Database Systems · Storage Engine · Query Optimization · Indexing
Papers bring me closer to the theoretical side. Articles force clarity. Code demonstrates execution.
Developed an agent-based Text-to-SQL system using Qwen-2.5-Coder-32B-Instruct with a multi-area architecture, MCP tool binding, and iterative validation loops. Evaluated on a Spider subset with hybrid similarity and SLM semantic equivalence metrics, and analyzed ambiguity/schema challenges with query reformulation strategies.
Explored four different text preprocessing strategies for sentiment analysis of Indonesian text, comparing them with a Gensim baseline. Contributed comprehensive evaluation framework using TF-IDF and SVM classification.
Proposed custom decision tree model to handle missing values during data splitting for nonlinear multivariate imputation tasks. Achieved notable average RMSE of 4.98 on synthetic educational dataset.
Developed forecasting model using SSA on daily food commodity prices in Bandung, Indonesia. Demonstrated SSA's ability to identify trends, seasonal patterns, and noise in non-stationary time series.
Writing is how I express what I think about programming. Hobbies, observations, technical views.
Reflection on how major university assignments can provide new perspectives in the rapidly evolving AI era.
DFS and BFS algorithms are fundamental algorithms, meaning all programmers should at least know about these two algorithms.
Decision Tree is one of the Machine Learning algorithms widely used for prediction. This article discusses the basic concepts of Decision Trees.
Experience and reflection during the first semester studying Informatics Engineering at Institut Teknologi Bandung.
Experience shows where I've applied my skills. Each role was about delivering specific results under real constraints.
Sep 2025 - Oct 2025
Legali AI
Architected orchestrated AI agents for pro se legal workflows, built a jurisdiction-aware RAG pipeline with OCR, parsing, PII anonymization, and region-filtered retrieval, and shipped document generation plus legal risk analysis with traceable outputs.
Agentic AI · RAG · OCR · PII Anonymization · Async Processing
May 2025 - Present
Fata Organa
Developed an agentic SQL QA system for a project management platform, automated spec generation, built a developer-task recommender, and benchmarked SLM inference with Ollama and vLLM to cut response time by about 2x.
SQL QA · Ollama · vLLM · Recommender Systems · Spec Automation
Sep 2024
MarkAny
Labeled 100+ frames per day across 10 object classes, maintained XML bounding boxes with strict guidelines, and helped standardize annotation procedures to improve consistency and model convergence.
Computer Vision · XML Annotation · Dataset QA
Unpaid work that sharpens skills and gives back. These roles tested my ability to design problems and validate solutions.
Nov 2024 - Present
ARKAVIDIA 9.0
Developed and structured data science and machine learning challenges for Datavidia, ensuring a diverse range of problem difficulties and real-world applications. Also conducted extensive data collection and feasibility testing on problems.
Impact: Ensured high-quality and relevant datasets for competition tasks and validated problem fairness.
May 2024 - Jul 2024
IMPACT ITB 4.0
Designed and formulated high-quality algorithmic and mathematical problems for the competition. Created problem sets across multiple domains and developed Higher-Order Thinking Skills (HOTS) problems to test participants' deep problem-solving skills.
Impact: Ensured a smooth and challenging experience for participants by providing fair and correct problems.
A way to remember what I've done. Visual memory of where I've been and what happened.
A pause within a shared moment.
Paths taken between obligations.
Tools arranged for quiet work.
Routine measured in steady stride.
Motion without intent to be seen.
Time held before moving on.
A moment passing without notice.
Scale felt through distance.
Presence caught in transit.
A frame that remains.
