Founding Engineer

Råvan Talani

From Uppsala to Marseille, via machine learning and a lot of TypeScript.

Founding Engineer·TypeScript·Machine Learning·Next.js·Node.js·MCP·Python·Azure·React·Marseille·Full Stack·AWS·Founding Engineer·TypeScript·Machine Learning·Next.js·Node.js·MCP·Python·Azure·React·Marseille·Full Stack·AWS·

About

I'm a Founding Engineer with an M.Sc. in Sociotechnical Systems Engineering from Uppsala University. I've spent the last three years building a Unified API from scratch at a German startup, connecting over 25 accounting and ERP systems.

My background spans everything from full-stack development to machine learning. I'm deeply passionate about AI and agentic engineering, and spend much of my free time exploring the possibilities and limits of what's possible. I'm always happy to connect with like-minded people and exchange ideas around side projects, experiments, or anything interesting being built with AI.

Currently based in Marseille, France, where I like to run along the Mediterranean coast, get lost in a good book, and occasionally disappear somewhere new on the map. You'll also find me travelling back and forth to Uppsala, Sweden, the city I grew up in.

Experience

2023 — Present
2023 — Present
Founding Engineer & AI Strategy Lead
Maesn GmbH (German Startup)Remote / Marseille
2023
2023
Graduated · M.Sc. Sociotechnical Systems Engineering
Uppsala UniversityUppsala, Sweden
2023
2023
ML Engineer — Thesis / Production
Kambi Group PlcStockholm, Sweden
2022
2022
Front-end Developer Intern
Kambi Group PlcStockholm, Sweden
2020 — 2021
2020 — 2021
Programming Teacher · Java & Python
Uppsala UniversityUppsala, Sweden
2018
2018
Graduated · International Baccalaureate Diploma
Katedralskolan UppsalaUppsala, Sweden

Full resume

Skills

Programming

TypeScript
JavaScript
Python
Java

Web Development

HTML
CSS
React
Vue
Node.js
Next.js
FastAPI

Databases

MongoDB
SQL
PostgreSQL
ChromaDB
Redis
Prisma

Data Science

Pandas
NumPy
R
MATLAB
SciPy
Excel

ML / AI

TensorFlow
PyTorch
LangChain
Keras
Scikit-learn
MCP

Cloud & DevOps

Azure
AWS
Docker
Git

Spoken languages

Swedish: Fluent
English: Fluent
Kurdish: Fluent
French: Intermediate
German: Elementary

Projects

MCP Server for AI Tool Connectivity

AI-to-ERP in natural language

Independently implemented an MCP server on top of the Unified API, enabling AI assistants to interact with accounting and ERP systems through natural language.

TypeScriptMCPNode.js

Football Stoppage Time Prediction

Shipped to production at Kambi Group

Developed a probabilistic ML model for predicting stoppage time in football matches, modelling outcomes as a convolution of negative binomial distributions. Shipped to production at Kambi Group and actively used for live betting odds.

PythonTensorFlowKerasScikit-learnAWS

In Progress

French Language Learning App

Active development

A mobile app for learning French, trying to make sense of the language that doesn't make sense. Built for more structured learning than traditional apps.

ReactTypeScriptVite

Coming Soon