Skip to content
View MariiaKrestenko's full-sized avatar
1 follower · 6 following

Block or report MariiaKrestenko

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
MariiaKrestenko/README.md

Hi, I’m Mariia — I build AI systems and spend a fair amount of time proving they’re wrong

I work mainly with Python, LLM APIs and RAG.

I’m interested in retrieval, evaluation, structured outputs and failure analysis — basically the parts that become important once “it gave me a good answer once” stops being an acceptable test.

Most of what I’m building at the moment comes back to the same question: how do you know the AI system is actually working?

🧠 AI Engineering

OpenAI LangChain LangSmith PyTorch scikit--learn

⚙️ Backend & Engineering

Python FastAPI Pydantic pytest Git

📊 Data

NumPy pandas

Mariia’s Mascot

Currently building
A technical RAG system over industrial PC datasheets — with metadata-aware retrieval, structured query analysis, LangSmith evaluation and grounded answer generation.


What I’m working on next
Generation evaluation | reranking | hybrid search | improving corpus-wide retrieval


Background
Software development background in Swift/iOS, with later training in data science, analytics and applied AI.


Pinned Loading

  1. industrial-pc-procurement-rag industrial-pc-procurement-rag Public

    Python