KACPER
SAKS
_
I build production ML systems and scalable backend infrastructure — from model training and institutional backtesting to real-time inference, monitoring and CI/CD.
Specializing in institutional-grade backtesting (CPCV, DSR, PBO) for quantitative trading platforms, high-performance Python backends, multi-agent LLM systems, and AI engineering — from RAG pipelines to autonomous agent architectures. Engineering discipline from aerospace applied to software.
BEng in Mechanical Engineering from Silesian University of Technology, currently pursuing a Master's in Project Management at Collegium Civitas while working full-time at Airbus Defence and Space. Alongside work and studies, completed 42 Warsaw — a tuition-free, peer-to-peer programming academy with no lectures or teachers, focused on project-based learning 24/7.
FEATURED
View all projects →QUANTBRIEF: AI-POWERED REAL-TIME MARKET INTELLIGENCE AGENT
Multi-agent financial intelligence platform built at Mistral AI Hackathon — 5-agent pipeline screening 30+ articles in <50ms each, analyzing full SEC filings in 256K context, and delivering multilingual audio briefings.
ESG COMPLIANCE AGENT: AI-POWERED REGULATORY ASSESSMENT
Enterprise ESG compliance system with local LLM, FAISS vector search, and automated ESRS gap analysis across 10 regulatory modules.
X_QUANT: INSTITUTIONAL-GRADE QUANTITATIVE TRADING PLATFORM
90K+ line Python platform for systematic quantitative trading with ML pipeline, live IBKR paper trading, and CPCV/PBO validation achieving Sharpe 1.236.
AIRBUS DOCUMENT ANALYZER: AIR-GAPPED AI SYSTEM
Fully offline document analysis application with local LLM, OCR, and semantic search for high-confidentiality environments at Airbus Defence and Space.