Skip to content
View Gclabbe's full-sized avatar

Highlights

  • Pro

Block or report Gclabbe

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
Gclabbe/README.md

@Gclabbe

📫 How to reach me

👀 I’m interested in Machine Learning / AI / Robotics / Computer Vision

... I have worked in all of these techs

Current focuses @ Vivun

Advanced NLG on Foundation models

  • Lead for Prompt Engineering and prompt management
  • Technical prompts leveraging model outputs to generate human expressive explanations
  • Integration of guardrails-ai
  • Prompt analysis through Weights & Biases (wandb.ai)
  • RLHF system established through Arize (arize.ai)

NLP for Calendar Event management

  • BERT modeling
  • Domain rules
  • Cosine Similarity
  • TF/IDF
  • XGBoost

Time series assessment of historical activities

  • Segmented Random Forest
  • Structured and novel methods for assessing model fitness
  • Bayesian data framework (older version)

MLOps development and restructure

  • Productized solution for Fargate ECS w/ Step Functions
  • Structured process for mass training on Sagemaker Training
  • Advanced visualizations using Plotly Dash
  • Graduated to visualization and reporting on Weights & Biases (wandb.io)
  • Adopted Arize for visualization of production model performance (arize.ai)
  • Developing full MLOps solution on Sagemaker & Bedrock utilizing MetaFlow

Previous jobs

  • CV -- Scuba Steve
    • Human-assisted rapid annotation
      • Pixellib
      • MaskRCNN on Tensorflow
      • DeepMask / SharpMask on PyTorch
      • Dash web app
    • Identify hands entering equipment during operation
    • Flare operational status
    • Robocar - hobby project to get autonomous car around a track
  • Predictive Maintenance
    • Oil pump behavior monitoring and tagging
    • Oil and Gas equipment downtime and PHM
  • Robotics
    • minor degree in Controls Theory
    • first eight years of career was micro-robotics ... digital controls theory
  • ML @ Seagate
    • Sr. Director of Corporate Division for ML & DS
      • Managed through CRISP-DM
      • Co-developed internal DS University
      • Lead ML over 14 data scientist
    • Sr. Director of Asia-wide team developing AI Failure Analysis of Hard Disk Drives
      • Massive Random Forest project to analyze 3M+ returned drives per quarter
      • Enabled finding true primary issues vs. "most recently returned."
      • Led to a significant reduction in quality control assessment
      • Ultimately reduced FA staff from 600 to 350
    • 90-day report on forecast problems reduced to 3 days

🌱 I’m currently learning

  • University of Texas Austin - MSAI - ECD May 2025
    • Reinforcement Learning -- in progress
    • Natural Language Processing -- in progress
  • Fourth Brain AI building with LLM - completed May 2023
  • Fourth Brain AI program on MLE - completed Oct 2021
    • Regressions
    • Neural Networks
    • Capstone: automated annotation and training with unknown objects in images
  • University of Colorado MS in Data Science - stopped to transfer to UT Austin program
    • Courses completed
      • Ethics in DS
      • Basics in HPC
      • Algorithms

Background

  • Years overseas running multi-country division

    • Worldwide ownership for Global Failure Analysis Strategic Planning
    • 7 campuses in Thailand, China, Malaysia, Korea, Singapore
    • Two years living in China, two years living in Thailand
    • WW Customer Service ... constant contact with key customers
    • WW Failure Analysis ... leadership for all 12 campuses
    • Massive project using Random Forest
    • Increased visibility to critical problems by 100%+++
      • Reduced staffing from 600 - 350 over three years
  • Before that, many leadership roles. Key skills

    • Project management
    • Firmware/software delivery (SCRUM / Agile)
    • Firmware task awareness/development
    • Multi-team collaboration
    • Strategic alignment between divisions

🌱 I have learned

  • Torch -- UT Austin NLP
  • Tensorflow2 -- Deeplearning.ai
  • John's Hopkin's -- Data Science in R
  • Stanford DS -- Machine Learning in Octave (Matlab)
  • Business Management -- Harvard Business School
  • Six Sigma Black Belt
  • Problem Solving & Decision Making -- Kepneger-Tregoe
  • Telecommunications -- BSEE
  • Controls Theory -- sub-degree during BSEE

Popular repositories Loading

  1. ut-msaio ut-msaio Public

    Publicly shareable content about the University of Texas MSAIO program

    Python 9

  2. mlx90640_python mlx90640_python Public

    Forked from leswright1977/mlx90640_python

    MLX90640 driver and sample python code

    C++ 1

  3. scuba_steve scuba_steve Public

    Your Rapid Image Annotation Assistant

    1

  4. PixelLib PixelLib Public

    Forked from ayoolaolafenwa/PixelLib

    Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/

    Python 1

  5. chatbot-gpt chatbot-gpt Public

    Playing with OpenAI API, Streamlit & Docker

    Python 1

  6. datasciencecoursera datasciencecoursera Public

    Repository for Johns Hopkins Coursera classwork