Skip to content
View stephenleo's full-sized avatar
🇸🇬
🇸🇬

Block or report stephenleo

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
stephenleo/README.md

👋 Hi there! My name is

Marie Stephen Leo

Most people call me Leo

Github dev.to badge dev.to badge dev.to badge

  • ⚡ I currently lead a team of Machine Learning Engineers and Data Engineers to architect and build data powered products using various technologies on GCP.
  • ⌛ My prior experience is in building AI/ML products in e-commerce, public relations and high-tech manufacturing industries using AWS, GCP and on-prem.
  • 🦄 I've developed entire Data products end-end (Algorithms, Data Engineering, Backend, Microservice middle layer and Frontend) in the Python and AWS/GCP ecosystems.
  • 🔥 I'm also a part time Data Science Instructor.
  • ✍️ In my free time I'm a Freelance Technical Writer. I'm a LinkedIn Top Voice (blue badge). I've achieved "Top writer in Artificial Intelligence" on Medium several times.
  • 💪 I have 14+ years of ML experience across NLP (including LLMOps), RecSys, MLOps, Data Engineering, Data Analytics, Computer Vision, and Tabular data. I’ve published multiple technical blog posts on Medium (1000+ followers) and co-authored a paper in ACL 2020 on unsupervised topic modelling of e-commerce reviews.

I regularly post about practical and applied data science. If you like my posts, let's connect on Linkedin or on Medium!

Pinned Loading

  1. llm-structured-output-benchmarks llm-structured-output-benchmarks Public

    Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on tasks like multi-label classification, named entity recognition,…

    Python 162 6

  2. stripnet stripnet Public

    STriP Net: Semantic Similarity of Scientific Papers (S3P) Network

    HTML 85 8

  3. adventures-with-ann adventures-with-ann Public

    All the code for a series of Medium articles on Approximate Nearest Neighbors

    Jupyter Notebook 45 12

  4. sagemaker-deployment sagemaker-deployment Public

    Jupyter Notebook 11 4

  5. BerriAI/litellm BerriAI/litellm Public

    Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

    Python 20.6k 2.6k

  6. pydantic/pydantic-ai pydantic/pydantic-ai Public

    Agent Framework / shim to use Pydantic with LLMs

    Python 8.4k 733