Hi, I'm Kerem
Machine Learning Engineer at EPFL Blue Brain Project, specializing in MLOps and LLM development. I bridge the gap between artificial intelligence and neuroscience.
Experience
Freelancer in AI and MLOps
Geneva
- Application of novel techniques in LLM systems (LoRA, QLoRA, DORA, MoE, SFT)
- Development and integration of agentic frameworks (Letta, LangChain, Swarm)
- Federated learning with Flower.ai
- Implementation of Model Context Protocols (fastMCP)
- Agentic monitoring and long-term memory solutions
Machine Learning Engineer
EPFL Blue Brain Project
- Led projects on semantic analysis of databases using Neo4j and Python
- Maintained and productionized AI software projects including LLM agents and GraphRAG
- Productionized AI chatbots with GraphRAG for unstructured data and graph databases
- Deployed AI software suite on Kubernetes and AWS
- Developed front-end applications for chat interfaces using React
Scientific Software Developer
EPFL Blue Brain Project
- Lead projects on building and analyzing large-scale brain region models
- Published research papers on Spiking Neural Networks and Graph Theory
- Maintained and productionized software using CI/CD pipelines
Student Ambassador in AI
Intel Nervana
- Designed machine learning models for analyzing fMRI data
- Showcased neuroscience research on Intel's AI platform
Software Engineer Intern
Neurolize
- Performed marketing research using EEG and eye tracking
- Analyzed online shopping interactions using classification techniques
Certifications
Neo4j Certified Professional
Neo4j GraphAcademy
2024
LLMOps
Deeplearning.ai
2024
AI Agents in LangGraph
Deeplearning.ai
2024
Fine Tuning Large Language Models
Deeplearning.ai
2024
Quantization Fundamentals in Hugging Face
Deeplearning.ai
2024
AWS Foundations
Amazon Web Services
2024
AWS Bedrock
Amazon Web Services
2024
Infrastructure as Code in Google Cloud Platform
LinkedIn Learning
2024
LLMs as Operating Systems: Agent Memory
Deeplearning.ai
May 2025
Federated Fine-Tuning of LLMs with Private Data
Deeplearning.ai
May 2025
Evaluating AI Agents
Deeplearning.ai
May 2025
Certifications
AWS Machine Learning Specialty
Amazon Web Services
2023
Neo4j Certified Professional
Neo4j GraphAcademy
2023
Deep Learning Specialization
Coursera
2022
LLMOps
deeplearning.ai
2024
Fine Tuning Large Language Models
deeplearning.ai
2024
Quantization Fundamentals with Hugging Face
deeplearning.ai
2024
Infrastructure as Code in Google Cloud Platform
LinkedIn Learning
2024
LLMs as Operating Systems: Agent Memory
Deeplearning.ai
May 2025
Federated Fine-Tuning of LLMs with Private Data
Deeplearning.ai
May 2025
Evaluating AI Agents
Deeplearning.ai
May 2025
Featured Projects
Biophysically Detailed Model of Rat Hippocampus CA1 Region
Developed and maintained in-silico models of detailed neurons in 3D rat atlas, validated by in-vivo and in-vitro experiments and provides insights into hippocampal function from its structure, physiology and connectivity.
Embedding Citation Graphs in VR
A 3D force graph visualization in VR using WebXR and Neo4j
Neuroagent: A multiagentic LLM for simulating and analyzing digital brains
Explore Literature and extract information to generate and simulate your own neuron models using our ChatGPT like interface, embedded into pay-as-you-go platform.
Sonata to Neo4j
Convert Biophysical Neuron Models and Simulations into Neo4j Graph and create fact sheets.
Chat with Brain
Talk to Brain Models with Large Language Models
Sortify
Sortify is a web application that allows users to sort their favorite Spotify album tracks based on their preferences.
Scholarag
A Retrieval Augmented Generation (RAG) API meant for scientific literature, which includes data management utilities and relevant endpoints for efficiently showcasing papers to your users.
Hypnosis Simulator
An interactive web application featuring various hypnotic visualizations and audio stimulations for relaxation and meditation. Includes multiple visualization types like Spiral Induction, Pulsing Light, and 3D Lorenz patterns, with customizable controls and audio accompaniment.
Publications
Machine and deep learning approaches for the study "Effects of early anesthesia exposure on human brain development using multimodal neuroimaging"
Kurban K., Budur E.
Poster - 16th National Neuroscience Congress in Turkey, 2018
Characterizing subtypes of projecting axons in mice using topological data analysis and machine learning
Kurban K., Kanari L.
Poster - Society for Neuroscience, San Diego, CA, USA, 2024
A connectome manipulation framework for the systematic and reproducible study of structure–function relationships through simulations
Pokorny, C., Awile, O., Isbister, J. B., Kurban, K., Wolf, M., & Reimann, M. W.
Journal - bioRxiv, 2024
A deep dive into CA1 network: Insights from Network Science
Kurban K, Romani A., Markram H.
Poster - 32th Computational Neuroscience Society, 2023
Community-based Reconstruction and Simulation of a Full-scale Model of Region CA1 of Rat Hippocampus
Romani, A., et al.
Preprint - Cold Spring Harbor Laboratory, 2023
Topological properties of full-scale model of rat hippocampus CA1 and their functional implications
Kurban K, Pokorny C., Romani A.
Poster - Society for Neuroscience, San Diego, CA, USA, 2022
Resting-state network dysconnectivity in ADHD: A system-neuroscience-based meta-analysis
Sutcubasi B, Metin B, Kurban MK, Metin ZE, Beser B, Sonuga-Barke E
Journal - World J Biol Psychiatry, 2020