Akmal Aufa Alim Silhouette

AKMAL AUFA
ALIM

AI & SOFTWARE ENGINEER

DOWNLOAD CV

ABOUT

I am an Informatics Engineering graduate (S.Kom) specializing in AI and Software Engineering. Proven capability in building end-to-end applications, from developing robust backends to designing AI-driven solutions like Retrieval-Augmented Generation (RAG) pipelines. Strong problem-solver focused on delivering scalable, real-world technical solutions.

Academic Background

September, 2022 — August 2026

Institut Teknologi Indonesia

Bachelor of Computer Science (S.Kom)
  • GPA: 3.51/4.00 (Cumlaude)
  • Thesis: Implementation of Agentic Hybrid Retrieval-Augmented Generation (RAG) on LLM-Based University Admissions Chatbot.
September, 2024 — December, 2024

RevoU Tech Academy

Data Analytics & Generative AI Program
  • Score: 80 (A)
  • Studi Independen Bersertifikat (MSIB) Batch 7

ADAPTIVE STACK

// Core Tech

Languages

PythonTypeScriptJavaScriptSQL

AI & Machine Learning

RAG ArchitectureLLMs (Google Gemini)LangChainLangChainVector Processing (SPLADE)Scikit-LearnXGBoostMediaPipeOpenCVPandasNumPy

Backend & API

FastAPIPydanticPydanticStreamlitStreamlitSQLModel

Databases

PostgreSQL (Supabase)MySQLVector DB (Pinecone)Redis

Frontend & UI

Next.jsReact.jsTailwind CSS

Tools & Infrastructure

DockerDocker ComposeGitGitHub Actions (CI/CD)Web ScrapingPlaywrightBeautifulSoup

EXPERIENCE

February 2025 — July 2025

Internship AI & Data Science

Kampus Gratis, PT Menara Indonesia

  • >Engineered an NLP-driven AI Virtual Assistant using FastAPI and LangChain, integrating GPT-4o with regex pattern matching and ML fallbacks to achieve >95% intent detection accuracy.
  • >Architected a dual-frontend ecosystem (Native Web & Streamlit) backed by SQLite and SQLModel, developing 16 REST API endpoints with <500ms latency and validating the pipeline against 50+ edge-case scenarios.
  • >Developed a predictive AI Credit Scoring feature utilizing an XGBoost Classifier to evaluate user risk profiles, performing feature engineering on tabular data to optimize decision-making parameters.
FastAPILangChainXGBoostSQLiteSQLModelStreamlit

September 2024 — December 2024

Data Analytics & Gen-AI Trainee (MSIB)

RevoU Tech Academy

  • >Processed and cleansed 3,130 rows of US Regional Sales dataset to identify profitability anomalies and operational inefficiencies.
  • >Architected interactive Power BI dashboards tracking critical metrics including Total Profit, Trendlines, and Quantity Sales by Channel.
  • >Extracted strategic insights highlighting distribution disparities (In-Store generating $1.88M vs Wholesale $0.58M) and formulated data-driven recommendations for seasonal demand optimization.
Power BIGoogle SheetsData AnalyticsData Visualization

Projects

[ 01 ]

HaloITI

Autonomous Hybrid RAG Agent (B.Sc. Thesis R&D)

  • > Spearheaded a B.Sc. Thesis R&D to modernize the university admissions system, designing and proposing a production-ready AI infrastructure for institutional deployment.
  • > Engineered a zero-bloatware Autonomous RAG Agent in Pure Python (bypassing LangChain) with a Pydantic-based 4-Pillars Tooling ecosystem, enabling dynamic intent routing across Slot-Filling, Guardrails, Hybrid Vector Search, and native Text-to-SQL.
PythonFastAPIGeminiPinecone+5 tools
View Case Study→
[ 02 ]

Student Early Warning System

Predictive ML Pipeline

  • > Architected a multi-scenario Machine Learning pipeline to classify university dropout risks across 7 academic semesters, achieving up to 81.3% peak accuracy and 75.0% recall using XGBoost and Random Forest.
  • > Engineered an automated data pipeline to process 3,000+ raw records and extract 7 time-series predictive indicators, optimizing an 80:20 imbalanced dataset via strategic threshold calibration (0.42).
PythonXGBoostScikit-LearnPandas+1 tools
View Case Study→
[ 03 ]

Posebrina

Real-Time Posture Detection System

  • > Engineered a real-time posture detection application achieving 87% accuracy by integrating MediaPipe (BlazePose) for spatial feature extraction with a lightweight MLP Classifier.
  • > Curated a custom dataset of 1,300+ structural pose keypoints and deployed the model to provide continuous, automated posture monitoring with a 30-minute warning threshold.
PythonMediaPipeOpenCVScikit-Learn+1 tools
View Case Study→
→

View Full Archive

Explore all 3 projects