CS @ Universitas Indonesia

Mariano Gerardus Senduk

Chasing the Horizon

Guided by the North Star of AGI

Computer Science student interested in how intelligence works and how to turn that understanding into systems that help people. I work across AI research and product engineering, with AGI as my long-term direction.

Current trajectory AI researchNeuro-symbolic AIProduct engineeringUseful intelligence

About

Current coordinates

COORD-01

Current position

Computer Science undergraduate at Universitas Indonesia since 2022. Currently working on my thesis at LEXIN.

Academic base
COORD-02

Core foundation

A foundation in mathematics, algorithms, and machine learning, developed through coursework, research projects, and software engineering.

Technical foundation
COORD-03

Exploration fields

AI research and product engineering, alongside an interest in business, finance, and how technology fits into people's work.

Areas I explore
COORD-04

North Star

Contributing to AGI by building useful, reliable, and understandable AI systems.

Long-term journey

Projects

Constellations of Work

Click a star to read the domain signal.

Selected projects

Selected project signals

Information Retrieval

Cross-Lingual Retrieval and Reranking (TP3)

Compared lexical, hybrid, and dense retrieval with multilingual rerankers over 3.19 million documents, placing 4th on the class Kaggle leaderboard and studying ranking-quality versus runtime trade-offs.

BGE-M3FAISS HNSWCross-encoder fine-tuningNDCG@10
Reinforcement Learning

Modeling Infectious Disease Outbreak for Optimal Government Intervention

Modeled pandemic response as an MDP in a stochastic four-city SEIRD Gymnasium environment, then compared PPO, A2C, and a restricted DQN baseline under health, economic, and budget constraints.

Reinforcement LearningMarkov Decision ProcessesStable-Baselines3Gymnasium
Deep Learning / Finance

IDX Intraday Stock Return Prediction using TCN

Developed a causal multivariate forecasting model to predict 15-minute future log returns for 100 target stocks on the Indonesia Stock Exchange, using high-dimensional market features, Temporal Convolutional Networks, baseline comparisons, and calibration for near-zero market movement.

Deep LearningTime Series ForecastingPyTorchMarket Data
Information Retrieval

A Preliminary Study of Grouping Strategies for ListT5 Reranking

Extended the inference procedure of ListT5, a listwise reranker based on Fusion-in-Decoder T5, by studying grouping strategies, tournament-style reranking, caching behavior, and BEIR benchmark trade-offs without retraining the underlying model.

Inference experimentsInformation RetrievalListwise RerankingBEIR Evaluation
Information Retrieval

Mini Search Engine

Built a complete mini search engine using Python, NumPy, SciPy, and FAISS, covering indexing, compression, TF-IDF, BM25 variants, WAND optimization, LSI retrieval, approximate nearest-neighbor search, and query evaluation.

Information RetrievalPythonBM25FAISS
Speech AI

Identification of Authentic and Forged Segments in Partially Spoofed Speech

Studied detection and localization of synthetic segments in speech using Wav2Vec2-XLSR features and temporal attention, reporting both utterance-level and frame-level error rates.

Speech Signal ProcessingDeep LearningWav2Vec2Research Writing

Journey

Journeys

2019-2022

SMA Lokon St. Nikolaus Tomohon

Built the competitive foundation through informatics contests, algorithmic problem solving, and early computer science discipline.

Experiences
  • Informatics club
  • KSN Informatika 2021 finalist
  • BNPCHS Informatics finalist
2022 - Now

Computer Science Student at Universitas Indonesia

Studying computer science while building projects across AI research, software systems, data, product work, and team-based engineering.

Experiences
  • Bachelor of Computer Science
  • Research projects in information retrieval, reinforcement learning, deep learning, computer vision, and speech processing
  • Full-stack, mobile, database, game, and functional programming course projects
Jan 2026 - Jul 2026

AI Product Engineering at Klaussa.com

Worked with end-to-end ownership in a startup, understanding legal-product workflows and delivering features across AI, backend, data, and frontend systems.

Aug 2026 - Present

Researcher Intern at LEXIN

Researching how LLMs can translate Indonesian judicial reasoning into readable symbolic representations while preserving the meaning of the source, at the Center for Legal Informatics, UI.

Experiences
  • Python prototype for preparing court passages, generating structured outputs, and reconstructing Indonesian text from the representation
  • Repeatable prompting and bounded-correction experiments with retained run artifacts
  • Source, representation, and reconstruction comparison to inspect missing or unsupported meaning; semantic evaluation remains ongoing
Now

Directed exploration

Connecting AI research, product work, digitalization projects, and business learning into a clearer long-term AGI trajectory.

Current Works
  • Undergraduate thesis on faithful translation of judicial reasoning at LEXIN
  • Self-organizing knowledge engine (pal) with CLI and MCP interfaces

Skills

Capability dashboard

AI / ML

Models, retrieval, evaluation

North-east technical orbit

Core
Python, ML fundamentals, AI coursework
Applied
RAG, embeddings, transformers, CV, speech
Growing
LLM evaluation, IR experiments, RL systems
SOFTWARE

Systems that ship

Builder orbit

Core
Python, TypeScript, Git, SQL
Applied
Next.js, Astro, FastAPI, Django, Docker, vector DBs
Growing
Static deployment, observability, scalable UX
PRODUCT

Making systems useful

Human workflow orbit

Core
Feature design, trade-off analysis, user flows
Applied
AI product iteration, evaluation planning, team coordination
Exploring
Strategy, business models, finance, market reasoning
BUSINESS

Strategic exploration

Market reasoning orbit

Core
Market observation, operations exposure, stakeholder communication
Applied
Market research, business management, Power BI, forecasting projects
Exploring
Finance, product-market reasoning, AI strategy

Self Blog

Log Along the Journey

Contact

Send a signal.

Open to conversations around AI systems, product ideas, research collaborations, and ambitious projects that push useful intelligence forward.