Open to internships
Khadim
Mbaye
AI and Big Data engineering student at ESP Dakar. Interested in data systems, Spring Boot services and machine learning.
I learn by building, one repository at a time.
Most projects start as a question I can’t let go of, and end as something people can actually use. I am a stay-at-my-desk person, so there is usually a terminal open next to whatever I am watching.
- Based in
- Dakar, Senegal
- School
- Ecole Superieure Polytechnique, UCAD
- Right now
- 3rd year DIC, AI and Big Data option
- Repositories
- 35 profile, 23 in the organization
Selected work
Data pipelines, Spring Boot services and AI agents.
Everything below is public, linked, and built from my desk in Dakar.
SenSante Pro
A medical consultation platform for Senegalese health facilities. Started as a four-sprint group project at ESP, then rebuilt solo on Spring AI, Docker and Terraform.
Lead Scoring Classifier
Homework 3 of the Machine Learning Zoomcamp: logistic regression on 5,000 leads, missing values imputed, features ranked by mutual information, then an Optuna search over C that pushed test accuracy from 0.67 to 0.73.
DeepMind Research Notes
Coursework, lab solutions and research notes from the whole Google DeepMind AI Research Foundations path, kept course by course. It starts with training a small language model.
Neural Networks I
Week 6 of MITx 6.036, solved: forward propagation, ReLU hidden units, decision regions in x-space, softmax outputs and the training dynamics behind them.
Neural Networks II
Week 7 of MITx 6.036: momentum, Adadelta and Adam, vanishing and exploding gradients, early stopping, weight decay, dropout and batch normalization.
NYC Taxi Pipeline
An ELT pipeline for 39.6 million New York taxi trips, from compressed CSV to Oracle Autonomous Data Warehouse, deduplicated by MD5 row hash.
What I work with.
languages
- Python
- Java
- JavaScript
- SQL
machine learning
- pandas
- NumPy
- scikit-learn
- PyTorch
- TensorFlow
- Keras
- Matplotlib
- Jupyter
data and back end
- Apache Spark
- Apache Airflow
- Hadoop
- PostgreSQL
- MySQL
- Spring Boot
- Spring AI
cloud and tooling
- AWS Bedrock
- Amazon S3
- Amazon EC2
- Docker
- Terraform
- GitHub Actions
- Linux
- React
Learning in public.
Every cohort is worked through in public repositories, homework included.
Two degrees at ESP Dakar.
-
2024-2027
DIC Informatique, Intelligence Artificielle et Big Data
Diplome d’Ingenieur de Conception (Bac+5), Genie Informatique. Ecole Superieure Polytechnique, Universite Cheikh Anta Diop.
Third and final year. Machine learning and deep learning, big data and data engineering, software process, and team projects such as SenSante Pro.
-
Completed
DST Informatique
Diplome Superieur de Technologie (Bac+2). Ecole Superieure Polytechnique, Universite Cheikh Anta Diop.
Algorithms, programming, databases, networks and applied projects, with the objective of conceiving and maintaining information systems that answer real user needs.
Certifications.
The ones that matter most for what I am building next, each one linked to its verification page.
- Big Data Foundations, Level 2 IBM, Credly
- Hadoop 101 IBM Cognitive Class
- Google AI Professional Certificate Google, Coursera
- Train a Small Language Model Google DeepMind
- Claude Code in Action Anthropic, Skilljar
- Fundamentals of Java Programming Coursera
- Databases Frontend Masters
- Complete Intro to Containers, v2 Frontend Masters
Download my CV.
Off screen.
I am a stay-at-my-desk person: long sessions, a lot of tabs, and anime or manga when I need to switch off. When the light is good I go out for sunset and sunrise photos, and anything quiet on the way back.
