AI Engineer & Researcher
I am a master’s student in Artificial Intelligence at Warsaw University of Technology with a strong foundation in machine learning, multi-agent systems, and game theory applied to AI. I currently work as an AI Engineer at AI Clearing, building production RAG systems and multi-agent architectures for complex analytical workflows. I have a growing track record of academic publications, including recent submissions to top-tier venues like ICML and DSS, as well as accepted papers at AAMAS (EXTRAAMAS), ICCS, PACIS (A-tier), and ACIIDS (Best Student Paper Award). I am passionate about creating robust, verifiable, and governance-aware AI systems.
Major: Artificial Intelligence
Thesis: Investigating the Application of Game Theory in LLM-based Multi-Agent Systems
Major: Automatic Control & Robotics
Thesis: AI Architectures for Option Pricing and Portfolio Management: Transformers to MAS
Proposes a hierarchical critic architecture for centralized training with decentralized execution that explicitly separates team-wide rewards from individual agent contributions. Validated on SMACv2 environments.
Investigates how multi-agent LLM deliberation can be organized as a governance-aware decision-support process. Evaluated using hedge-fund portfolio allocation, demonstrating stronger downside protection during extreme regime shifts.
Introduces Explanatory Equilibrium as a design principle for explanation-aware MAS. Models LLM communication as a signaling game to derive validation bounds preventing cheap-talk degeneration.
Proposes a hybrid architecture where an LLM produces structured allocation decisions conditioned on retrieved historical precedents, and execution is grounded in canonical option strategies.
Accepted to PACIS (A-tier per CORE). Presents a multi-agent RL framework that ensembles options-based hedges to improve risk-adjusted returns and stabilize portfolios in volatile markets.
Integrated neural networks, volatility modeling, and sentiment analysis via LLMs into a hybrid option pricing model. Designed an RL trading strategy.
Compares Informer, Autoformer, FEDformer, and Pyraformer against classical models and deep sequence baselines across equities, indices, and crypto options.
Explored the Informer—a Transformer-based model—for option pricing, adapting it to handle long-sequence modeling capabilities to enhance prediction accuracy.
Architected and deployed a production multi-agent LLM system (LangGraph, LangChain). Designed a domain-specific RAG pipeline handling complex construction data (Excel, nested tables, marked-up PDFs) via OCR, vision LLMs, BM25, and reranking.
Impact: Increased system accuracy from 78% to 98%. Reduced latency (80s → 20s) via caching and token usage (1.1M → 200k) via selective tool-based routing.
Developed Python-based automation tools and data pipelines. Analyzed market trends and optimized strategies to support business operations.
Built React (TypeScript) and .NET micro-frontends, implemented REST APIs, and integrated backend logic in cross-functional Agile teams.
Leading a student research group focused on generative AI, multi-agent systems, LLM applications, and argument modeling. Promoting practical AI applications in finance and decision systems.
Led AI/LLM-oriented student projects, organized tech-business meetups, and managed a 10-member team delivering workshops and hackathons in Warsaw.
Collaborated on entrepreneurship projects addressing social challenges through innovation, with emphasis on leadership and cross-functional teamwork.
Received research funding to support the development of multi-agent architectures and cognitive systems applied to intelligent information networks.
Awarded for outstanding academic achievements and continued scientific development in the area of cognitive architectures and MAS in intelligent systems.
Honored for the paper "Options Pricing Platform with Neural Networks, LLMs and Reinforcement Learning" at the Asian Conference on Intelligent Information and Database Systems.