My profile image

Hi, I'm Leo Kravtchin!

Ambitious business intelligence and data engineer with 3+ years of experience across Amazon FinTech / Accounting Technologies and Operations, METRO Markets, and several start-ups. Specialised in Python, AWS, and SQL for data pipelines, machine learning, and metrics automation. Master’s degree in computer science and AI from the University of Edinburgh, specialising in AI for healthcare.


Highlights Resume

Here are some of my recent highlights


BIE at Amazon

Business Intelligence Engineer in Accounting Technologies, working on Python and AWS automation projects.

Amazon GenAI

Amazon GenAI and agentic AI hackathon applications using AWS RAG knowledge bases and MCP servers.

Master's Degree

Completed my master's degree in AI and computer science from the University of Edinburgh.


Examples of projects and accomplishments

Due to company and university policies, all sourcecode and sensitive details must remain private


Thesis result example

DelphAi: Amazon ORC Hackathon 2025

In a team of 4, we developed an AWS Lex chatbot using Bedrock, a RAG knowledge base, API Gateway, Amplify, S3, and Lambda to add documents to the RAG model. The chatbot answers questions about Amazon domains, based on documents uploaded by the user through the UI.
AWS Bedrock, API Gateway, Amplify, S3, Lambda, Lex, React, Python, JavaScript

Thesis result example

SlackOracle: Amazon UK&I Generative AI Hackathon 2024

In a team of 5, we developed an internal Slack bot that uses AWS Bedrock, a RAG knowledge base, API Gateway, Lambda, S3, and OpenSearch to answer users' questions about a Slack channel's history. New Slack channels are ingested into the knowledge base through a Slack bot interface, allowing onboarding to new channels.
AWS Bedrock, API Gateway, Lambda, S3, OpenSearch, Slack

Thesis result example

Master's Thesis

Interpretable and Trustworthy Machine Learning for ICU Admission Length of Stay and Mortality Predictions, supervised by Dr Sohan Seth. Using machine learning and data science techniques for hospital patients' mortality predictions and length of stay predictions.
Python, TensorFlow, Scikit-Learn, PM4Py, Prophet, NeuralProphet, Git

Thesis result example

BSc Thesis - 77%

Detecting Long-Term Deviation and External Factors Correlations in Activities of Daily Living Based on Sensor Data, supervised by Dr Jacques Fleuriot. Using machine learning and deep learning techniques for human activity recognition, clustering, process mining, and activity forecasting.
Python, TensorFlow, Scikit-Learn, PM4Py, Prophet, NeuralProphet, Git

Snippet homepage

Snippet. - 69%

In a team of six, we developed a full-stack web search engine for 10m Spotify podcast transcript snippets, enabling users to search for and listen to only the parts of podcasts and topics they are interested in. Implemented features include ranked information retrieval, semantic search, topic modelling, query expansion, and CI/CD using Jenkins via GitHub.
Python, Flask, React, PostgreSQL, MongoDB, Docker, Google Cloud, Jenkins

Confusion Matrix

RecognisED - 88%

We developed a full-stack mobile app for real-time human activity recognition from wearable sensors in a team of three. We used deep learning to achieve classification accuracies of 94% for 4 activity subsets and 72% for 14 different activities. The app shows the classified activity, step count, and stores historical user data using Firebase.
Python, TensorFlow, Keras, Scikit-Learn, Java, Kotlin, Firebase, Git

AIML Group

AIML Research Talks

I am a member of AIML, the Artificial Intelligence Modelling Lab research group at the University of Edinburgh's AIAI institute (Artificial Intelligence Applications Institute). I held two talks about my dissertation's research goals, proposed methods, and concluded findings as part of my viva preparations. I also regularly attended other research talks, learning about state-of-the-art machine learning applications.

Metro Markets logo

Internship Projects

  • Created a Slack Bot for hourly production data insights using JavaScript, MySQL, and Google Cloud Kubernetes. This tool served as a safety net to engineering teams.
  • Set up data pipelines for performance analysis of internal systems based on complex read & write MySQL queries.
  • Automated first-respondence and post-mortem analysis of wrong pricing incidents using MySQL querying and Python analysis.
GitHub logo

Full-Stack Web Development

  • This website is open-source and uses HTML, CSS, SASS, JavaScript, and jQuery. It is hosted and updated using CI/CD via GitHub Pages.
  • Full-stack web development for Liedfestival Kassel, including a ticket booking system with seat reservations, email confirmations, and a SQL database using the Django web framework.
  • Front-end web development for GetTransfer.com, end-to-end.

Contact Form



Find me on ...