Skip to content
View tommygrammar's full-sized avatar
2 followers · 5 following

Block or report tommygrammar

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 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
tommygrammar/README.md

Hi there! I’m Tom Muga, a Machine Learning Engineer experienced in building, deploying, and scaling data-driven systems for real-world business applications. Skilled in designing end-to-end ML pipelines, integrating models into production APIs, and collaborating with cross-functional teams to deliver measurable business outcomes. Focused on efficiency, scalability, and translating data into actionable insights.

🛠️ Tech Stack

  • Languages: Python, Flask
  • Data Analysis & Visualization: Numpy, Pandas, Matplotlib, Seaborn
  • ML & Deep Learnin: TensorFlow, PyTorch, scikit-learn, regression, classification, clustering, LLMs
  • Cloud Platforms: Azure
  • Database & Tools: PostgreSQL, Redis, MongoDB, RabbitMQ
    • Vector DB: Chroma
    • ML Ops & Monitoring: Airflow, Prometheus, Grafana, Docker, Kubernetes
    • Development Practices: Git

💬 Get In Touch

Pinned Loading

  1. eventimpact eventimpact Public

    A lightweight, production‑grade Python toolkit to quantify the impact of any bounded event (e.g. limited‑time promotion, marketing campaign, feature release) on a time‑series metric..

    Python 1

  2. IntentMatcher IntentMatcher Public

    A lightweight Natural Language Probabilistic Intent Engine designed to match free-form user queries to predefined intents using a hybrid of similarity metrics and Bayesian scoring. Ideal for chatbo…

    Python 1

  3. emergent-revenue-forecast emergent-revenue-forecast Public

    A lightweight, two-layer Bayesian model that infers which revenue quintile your business is likely to land in—based on three core KPIs—and back-tests its own accuracy.

    Python 1