Ivan Milev
I'm a Programmer
About
Hey, I'm Ivan, a software engineer from Bulgaria, passionate about both Machine Learning (ML) and Software Engineering. I'm lighthearted, always up for a good laugh, and enjoy working with new people. My main focus is exploring the crossover between ML and SE, where I believe the lots of exciting innovations are happening.
Machine Learning Researcher and Software Engineer
"Love everything Machine Learning, love everything Software Engineering."
- Birthday: 2 April 1999
- City: Zurich, Switzerland
- Spoken Languages: English, Bulgarian
- Degree: CS Master ETH Zurich
- Experience: 5+ years in Software Engineering and ML Research
- Email: ivan.i.milev@gmail.com
In my free time, you'll find me biking (BMX), longboarding, gaming (League of Legends), or hitting the slopes to ski in Switzerland's beautiful Alps.
Resume
Sumary
Ivan Milev
Customer-focused Software Engineer with experience in Machine Learning research. I'm highly goal-oriented, passionate about building solutions that address real-world problems. I've worked closely with customers and believe deeply in creating applications that truly meet their needs. Currently, I'm aiming to leverage these skills to start my own venture.
- Large Language Model Agents researcher
- Professional experience as a full stack developer
- Machine Learning for binary code research experience
Education
Computer Science Master | Machine Intelligence
2022 - 2025
ETH Zurich, Switzerland
I’m nearing the completion of my Master’s degree at ETH Zurich, where I focused on Machine Learning. My coursework includes subjects like Deep Learning for Big Code, Large Language Models, Natural Language Processing, Probabilistic Artificial Intelligence, Machine Perception, Computer Vision, and Big Data.
Bachelor of Engineering | Computer Engineering
2018 - 2022
Technical University Sofia, Bulgaria
Graduated 1st in class. During my bachelor’s, I studied both Electrical Engineering and Computer Science, but my heart was always with Computer Science. In my final years, I focused on application-based courses to sharpen my practical skills.
Professional Experience
Research Assistant/Project Intern
2023 - 2024
Reliable, Intelligent Systems Lab, ETH Zurich, Switzerland
- Machine Learning for binary code.
- Read and analyse papers, generate ideas for research topics.
Software Engineer (from Internship to SWE II)
2018 - 2022
Appfire formaly known as Botron Software, Sofia, Bulgaria
- Work with JVM based ecosystem with Java and Kotlin
- Optimize memory usage by implementing custom lazy loading
- Develop scalable cloud micro-services in VPC on AWS
- Talk to customers to resolve issues
- Present upcoming features to customers
Software Engineer Internship
2017
Accedia, Sofia, Bulgaria
- Backend development with C#, ASP.NET, ASP.NET MVC
Projects
Here's a selection of projects I completed during my studies at ETH Zurich and TU Sofia.
🕵️ ToolFuzz - Automated Testing for Agent Tools
ToolFuzz is the first-ever framework designed to rigorously test the correctness and robustness of LLM agent tools. Combining advanced fuzzing techniques and LLMs, with sophisticated correctness evaluation, ToolFuzz dynamically generates a vast range of test prompts, ensuring your tools can handle real-world scenarios.
CodeBoarding — Google Maps for Codebases
CodeBoarding turns complex systems into interactive maps, letting developers navigate from architecture to functions with ease. Share map sections as agent context, set guardrails by limiting which subsystems can be edited, and track agent impact in real time directly on the map.
Minimalist GPU Monitor for JetBrains
A plugin offering live monitoring of GPU utilization, including GPU memory usage, utilization percentage, and power consumption. Get live, minimalistic updates on GPU performance directly within your IDE.
A Multi-Model Ensemble For Robust Road Segmentation Using Staged Training
The goal of this project is to develop an automated solution for road segmentation...
Codex code generation based on Acceptance Criteria
This project is designed to help developers write tests by extracting information and generating tests based on code changes in Git, along with the acceptance criteria defined for each feature.
Facebook page assistant
This bot identifies hate speech comments on your Facebook page and leverages Stack Overflow to respond to direct messages.
It is implemented using standard Machine Learning algorithms, along with RAKE for the Q&A functionality.
Contact
If you’d like to reach out to me for projects or any inquiries, I’d be more than happy to hear from you!
Address
Casar Ritz Strasse 5, Zurich, Switzerland
Email Me
ivan.i.milev@gmail.com