Skip to content
View A-Kuo's full-sized avatar
0 followers · 2 following

Achievements

Achievement: Pull SharkAchievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report A-Kuo

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
A-Kuo/README.md

Austin (A-Kuo)

Data Engineer building ML-ready pipelines - ETL, streaming, and model infrastructure.

Focus areas

Data pipeline design - ETL/ELT, orchestration with Airflow, warehousing in BigQuery

ML infrastructure - multi-cloud inference routing, model calibration, uncertainty quantification

Applied ML - LLM fine-tuning, transformers, NLP, hallucination and uncertainty detection

crosscloud-ml-orchestration - Entropy-based multi-cloud ML inference router (GCP Vertex + AWS SageMaker) with Airflow orchestration, BigQuery telemetry, and isotonic regression calibration

Fine-Tuned-SEC-Filing-Extraction-Pipeline - QLoRA fine-tuned Llama 3.1 8B for structured extraction from SEC EDGAR filings

Language-Model-Hallucination-Detection-via-Entropy-Divergence - LLM hallucination detection using Shannon entropy divergence and uncertainty quantification

Transformer-Aspect-Based-Sentiment-Analysis - Fine-grained transformer ABSA with financial and clinical domain adaptation

Formula-1-Data-Strategy-System - Dynamic data pipeline and dashboard for race telemetry and lap-time modeling

[Deployed Stuff] https://share.streamlit.io/user/a-kuo

Tech

Python, PyTorch, Spark, Airflow, BigQuery, AWS, GCP, SQL

Pinned Loading

  1. Language-Model-Hallucination-Detection-via-Entropy-Divergence Language-Model-Hallucination-Detection-via-Entropy-Divergence Public

    LLM hallucination detection using Shannon entropy divergence and self-referencing uncertainty quantification

    Python 1

  2. Fine-Tuned-SEC-Filing-Extraction-Pipeline Fine-Tuned-SEC-Filing-Extraction-Pipeline Public

    QLoRA fine-tuned Llama 3.1 8B for structured extraction from SEC EDGAR filings — financial NLP, chunking, and document understanding

    Python 1

  3. Transformer-Aspect-Based-Sentiment-Analysis Transformer-Aspect-Based-Sentiment-Analysis Public

    Fine-grained transformer ABSA with financial and clinical domain adaptation

    Python 1

  4. crosscloud-ml-orchestration crosscloud-ml-orchestration Public

    Entropy-based multi-cloud ML inference router across GCP Vertex and AWS SageMaker with Airflow, BigQuery telemetry, and isotonic regression calibration

    Python

  5. Formula-1-Data-Strategy-System Formula-1-Data-Strategy-System Public

    Building off of a previous microservice styled protoype dashboard for measuring race metrics for optimized lap times, this project permits dynamic data refreshes and model training

    Python