cv

This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.

Basics

Name Adam Kaniasty
Label Data Scientist & AI Engineer
Email adam.kaniasty@gmail.com
Url https://github.com/AdamKaniasty
Summary Co-Founder and CTO of APPI, passionate about AI, ML, and building AI-driven solutions for real-world problems.

Work

  • 2023.02 - Present
    Co-Founder / CTO
    APPI
    Leading AI-driven projects focused on Retrieval-Augmented Generation (RAG) and deploying NLP models for the construction and architecture industries.
    • Developed internal tools using FastAPI
    • Led multi-container deployment on Docker
    • Integrated GPT models into web apps
  • 2022.07 - Present
    Working Student / ML Engineer / Software Developer
    Nokia
    Worked on Kubernetes pod autoscaling using RL models, developed NLP-based applications, and contributed to CI/CD pipelines using Jenkins.
    • Designed and deployed RL (DDQN) model
    • Used TensorFlow, LangChain, Pinecone for NLP solutions
    • Managed Jenkins CI/CD pipeline

Education

  • 2022.10 - 2026.02

    Warsaw, Poland

    Bachelor’s Degree
    Warsaw University of Technology
    Data Science
    • Calculus II
    • Theory of Probability
    • Statistics
    • Algorithms
    • ML
    • Data Visualization
    • Databases

Projects

  • 2023.02 - Present
    APPI Synapse
    An internal tool for information retrieval using RAG techniques, developed for the architecture and construction industries.
    • Integrated React, FastAPI, and MongoDB
    • Leveraged LlamaIndex and LangChain for document processing
  • 2023.02 - Present
    APPI Marketplace
    AI-driven expert marketplace web app with fine-tuned GPT models for context-based responses and knowledge discovery.
    • Built GPT-based expert system
    • Deployed with FastAPI and Docker
  • 2022.01 - 2022.12
    Terrain Segmentation Models
    Developed terrain segmentation models for the CanSat competition using PyTorch and transfer learning with ResNet12.

Awards

  • 2022.12.01
    CanSat Finalist
    CanSat
    Finalist in the CanSat competition for developing terrain segmentation models using PyTorch.

Skills

Machine Learning
TensorFlow
PyTorch
Sklearn
Numpy
LlamaIndex
Data and Visualization
SQL
Pinecone
R
Programming
React (TS)
C++
Linux
Docker

Languages

Polish
Native speaker
English
C2 (CAE certificate)

Interests

AI and ML
NLP
RAG techniques
Fine-tuning GPT models
Sports
Tennis
Martial Arts