Ivan Poliakov

ML Engineer | LLM Agents for Social Media | Computer Vision | Python/C++

I am Ivan (Vanya) Poliakov, an ML engineer and freelancer
specializing in AI for SMM, Computer Vision and taking AI Web Apps
from concept to production.

Recent work:
- Translation and content adaptation platform for X accounts
(300k+ followers) using LLM agents with topic clustering and few-shot learning
- Agentic frameworks for automated content suggestions
- A/B testing pipelines for viral content optimization

Available for:
- Social media agents and LLM integration
- Content generation and recommendation systems
- Computer Vision projects
- Data processing and scraping
- ML prototypes and Python, C++ development

Fast turnaround, clear communication, ready to start immediately.

CV · GitHub · Codeforces · LinkedIn

Pet Projects

Robotic arm playing Beer Pong autonomously

Fine-tuned YOLOv6 object detection model to detect the cups and track the ball from the overhead camera. Implemented robotic arm control with adaptive aim correction.

3D renderer in C++ with zero dependencies

The renderer loads an .obj file, optionally a texture file, and paints a scene into a .tga file. It supports basic lighting and camera movement, z-buffer, Gouraud and Phong shading models.

Pentomino Tetris with autoplay

Pentomino tetris setup for gaming and autoplay simulations. You can play yourself or run an autoplay visualization. Autoplay was trained with a genetic algorithm.

3D image-stitching tool

A 3D image-stitching tool that aligns two overlapping photos (e.g., from a panorama) by estimating their homography transform with robust regression and warping one of the images onto the other.

Tech Stack

Programming Languages: Python, C++, JavaScript, Java

ML & Deep Learning: PyTorch, scikit-learn, Transformers, LangChain, NumPy, SciPy, statsmodels

Data & Visualization: pandas, OpenCV, Matplotlib, seaborn

Full-stack Development: FastAPI, Django, React, Qt, MongoDB, PostgreSQL

Tools & Platforms: Docker, Git, CI/CD, Linux, Google Cloud Platform

Education

2024 - 2026

MSc in Artificial Intelligence at Maastricht University

Internship: In fall 2024 I did data mining and developed agentic frameworks for a stealth startup.
Competitions: In fall 2024 I formed the first team in the history of my university to go to ICPC NWERC, quarter-finals of arguably the most prestigious programming competition in the world.
Research: Currently laying out preparation research for my MSc thesis.

2019-2023

BSc in Data Science at Maastricht University

Internship: In fall of 2021 I worked on a similarity search model for a legal referencing company Garant.
Thesis: My BSc thesis was about pretraining a conditional StyleGAN model from scratch on limited resources.