Bogdan Andrei

Lead a team of 4 building a multi-agent system that migrates legacy code, for example SQL stored procedures to C#, on projects over 100K lines. Agents pull code context through MCP servers and compare screenshots of the old and new UI through browser automation.

Freelance AI engineer working on various projects.

Worked directly with UK customs brokers to learn the import declaration process and turned their daily workflow into product decisions and customs rules kept as data. Main contributor to the first production version and rebuilt the platform as a TypeScript monorepo.

Automated splitting IT tickets into solvable subtasks. Benchmarked CoT, Tree of Thoughts, LATS, ReAct, Reflexion and multi-agent setups on shared metrics, and shipped the best ones into the product.

Built a RAG search engine over 400,000 legal documents that returns the relevant passages and a plain-language answer in 10-15 seconds.

Built the request router for the xPortal assistant. Each query type went to its own LLM agent that could run calculations, call pricing APIs or write and run SQL.

Led a small team that took a WhatsApp booking agent from concept to production for a platform serving 700 partner salons and 180,000 active users.

Cut inference time and model size by up to 10x with quantization, pruning and compilation, without losing accuracy. Took a named entity recognition project from concept to production, reaching 98% F1 on the main classes.

Recorded 50+ hours of machine learning video lessons for 30+ students and ran labs in web development and PLCs.

Worked on 7+ research projects applying deep learning to cardiac MRI. The work produced 4 patent filings (2 granted in the US, first inventor on 3) and a first-author journal paper. Built 3 annotation tools for time-series and 4D medical data.

Built keypoint regression and object detection on RGB-D streams for a smart lamp, plus an automated pipeline for collecting and labelling data.

Redesigned SIFT feature matching for medical images with deep learning (VGG16, KD-tree). Presented a poster at the EEML summer school.

Doctoral studies in Systems Engineering, not completed. Research focused on AI for assessing cardiovascular disease from cardiac MRI.

MSc in Cyber Security with a thesis on AI-based malware classification.

BSc in Automation and Applied Informatics with a thesis on AI-based feature matching for medical imaging.