🎓 Third-year undergraduate at the National University of Singapore
📚 Double Major: Data Science & Analytics + Computer Science (AI/ML concentration)
📊 Passion: Building scalable ML & analytics systems that bridge research and business impact

• GIC Internship – Quantitative Strategist (2025)
  Refactored climate alignment pipelines into modular packages, improved runtime by ~40%, and delivered CEO-level risk monitoring outputs.

• ESG Data Extraction & Performance Analysis
  End-to-end pipeline combining OCR, RAG, and LLM parsing → cut manual due diligence by ~60%, 78.9% accuracy on KPI extraction, Dockerized workflows, live Power BI dashboards.

• Toxic Comment Projects

  • Classifier (DistilBERT): Fine-tuned model reaching 0.947 F1 on 150K samples.
  • FastAPI Service: Deployed a REST API supporting 1,000-char inputs with feedback monitoring to simulate real-world robustness.

👉 ESG Data Extraction & Analysis – OCR + LLM pipeline, Docker, dashboards
👉 Toxic Comment Classifier – DistilBERT model training & evaluation
👉 Toxic Comment API – FastAPI REST service with monitoring

Languages: Python, SQL, Java, R
ML/AI: PyTorch, TensorFlow, HuggingFace, Scikit-learn, LLMs (RAG, fine-tuning, prompt engineering)
Data & Tools: FastAPI, Docker, Pandas/NumPy, Power BI, Tableau, Git, Selenium, SQLite

LinkedIn • Resume PDF • Email: jaejun.shim@outlook.com