Project Portfolio

Adityo Nugroho | AI/ML Engineering

Back to Main Portfolio

1

Live Deployment

5.6M

Data Records

3

Integrated Suites

Project 01

Incident Commander

AI/ML Engineering

Event-driven log analysis system processing high-velocity log streams with tumbling window batching. Features async architecture with cascading AI triage for critical event detection and semantic root cause clustering.

Gemini 2.0 Flash Lite Python Async Event-Driven Pydantic
Project 02

NOC Oracle

AI/ML Engineering

RAG-powered autonomous runbook with hallucination prevention. Maps specific error codes to exact repair procedures from technical manuals, eliminating hallucination risk with hybrid search and strict context enforcement.

Gemini 2.0 LangChain ChromaDB Text Embedding
Project 03

Net-Ops Agent

AI/ML Engineering

Agentic AI with human-in-the-loop safety guardrails. Translates natural language operational commands into safe, deterministic Python function calls with mandatory approval gates preventing unauthorized executions.

Gemini 2.0 Function Calling Streamlit HITL
Project 04

Google Cloud AI Studio

AI/ML Engineering

Multi-step GenAI workflow for architectural design on Google Cloud. Orchestrated pipeline transforming text descriptions into photorealistic renders through three stages: text enhancement, sketch generation, and rendering.

Vertex AI Gemini 2.0/2.5 Cloud Run Docker
Project 05

Telecom Digital Twin

Data Engineering

Deterministic multi-table telecom data generator with causal ordering. Produces realistic telecom tables with bit-exact reproducibility via cascading seed propagation and Parquet schema validation.

Parquet SDV Pandas Deterministic
Project 06

Telecom QoE Analytics

Data Science

End-to-end analytics pipeline from EDA to strategic insights. Comprehensive data science practice with statistical rigor, SHAP interpretability, and high-performance ML models identifying congestion as primary QoE driver (Cohen's d = -2.12).

XGBoost LightGBM SHAP Optuna
Project 07

Telecom ML Framework

ML Engineering

Production-ready framework for telecom AI/ML solutions. Covers 6 telecom ML use cases with complete technical specifications, domain-informed data generators, and unified technical standards.

XGBoost LightGBM SHAP Cookiecutter
Project 08

Trailing Edge Trading Bot

Quantitative Trading

High-performance async trading bot with dynamic trailing take-profit. Features regime detection, Donchian channel gating, and Ed25519 authentication. Deployed as systemd service for 24/7 autonomous operation.

Python Async WebSockets Ed25519 Systemd
Project 09

RATU FIX Bot

Quantitative Trading

FIX protocol connector for Binance with defensive message parsing. Three FIX sessions (Market Data, Order Entry, Drop Copy) with ED25519 authentication and spread market making strategy.

FIX 4.4 ED25519 Binance SDK Market Making
Project 10

RATU REST API

Blockchain & Trading

Comprehensive market analytics using Binance public REST API. Multi-endpoint integration with dataclass-based parsing, connection pooling, and multi-timeframe analysis for complete market snapshots.

Binance API httpx Dataclasses Multi-TF
Project 11

RATU On-chain Monitor

Blockchain & Trading

On-chain token holder analytics and whale tracking. Three-mode architecture with pagination handling, known label identification, and snapshot comparison for tracking holder changes over time.

Ankr API httpx Pagination Labels
Project 12

RATU Moon Radar

Blockchain & Trading

Multi-chain DEX pair scanner and early token detector. Real-time token discovery with connection pooling and multi-chain support across Ethereum, BNB Chain, Polygon, and Base.

Moralis API httpx Multi-Chain Pooling