Daniel Huber — Team Lead, Financial Technology @ Leonteq · Zürich
Building AI agent systems in fintech.
Python · LangChain · LangGraph · RAG · Local LLM · C# · 10+ yrs
# AI systems journal — topics auto-collected by agent, deployed via GitHub Actions
Recently delivered an AI agent proof-of-concept for research report analysis using multi-model pipelines and semantic search. Team Lead at Leonteq with 10+ years in financial technology.
Leading a team of 4 developers across Zürich and Lisbon. Handling incident resolution and operational risk analysis across time zones (Singapore to Europe).
Over the past decade I've progressed from analyst to director, working across pricing/analytics, regulatory projects (MiFID II, SFTR, FRTB), and platform migrations. Currently contributing to AI Foundry initiative - deploying local LLM infrastructure and RAG applications.
Leading a team of 4 developers across Zürich and Lisbon. Handling incident resolution and operational risk analysis across time zones (Singapore to Europe).
Implemented generic booking model for mirror booking, reducing client onboarding complexity. Key contributor to LIBOR migration.
Progressed through multiple roles focusing on automation, risk management, and regulatory compliance.
Focused on reporting automation and distributed system implementation. Automated creation of listed instruments via SmartCo integration.
Bachelor's degree in Computer Science with focus on practical software engineering, algorithms, and system design. Completed several industry-relevant projects including algorithmic trading, GPU programming, and financial portfolio management systems.
Mathematics studies at ETH Zürich. Built a foundation in linear algebra, calculus, probability theory, and mathematical analysis. Transitioned to applied computer science to focus on practical implementation of mathematical concepts.
Neural networks, CNNs, RNNs, sequence models, and deep learning optimization techniques.
View Course →Agent architectures, tool integration, Google ADK. Built Backtest-Agent for Kaggle competition.
View Badge →Supervised/unsupervised learning, neural networks, deep learning fundamentals.
View Certificate →Linear algebra, calculus, probability, statistics.
View Certificate →Investment strategies, risk management, complex financial instruments.
View Certificate →Personal projects applying ML/AI and agent development to financial technology
An AI systems journal where topics and news are automatically collected by an agent, pushed to the repo via GitHub Actions, and trigger a fresh deployment — no manual writing involved. The interesting part is the architecture: agent → content extraction → commit → CI/CD → live site.
End-to-end agentic pipeline that ingests research reports (investment bank PDFs), extracts semantic meaning, and matches trends to structured products. The agent identifies relevant underlyings (shares, indices), queries the product database, retrieves termsheet descriptions via RabbitMQ, and scores product-trend alignment. Uses a two-stage scoring approach: lightweight local LLM for fast batch processing, then larger model for top-50 refinement. Generates reports for products exceeding 0.75 alignment threshold.
Can AI Agents Learn to Trade by Watching AI Trade? An experiment in agentic learning where AI agents compete on live crypto markets while an Observer Agent watches, learns what works, and writes reusable skills for future agents.
Trading strategy backtesting agent developed for Google's 5-day intensive agent course Kaggle competition. Built using agent frameworks to automate trading strategy analysis and optimization. Practical application of LangGraph and agent development concepts learned in recent training.
Ethereum transaction analysis tool for visualizing ETH transfer networks. Includes multiple visualization modes and analytics features such as pattern analysis, gas insights, and basic anomaly detection. Built with React.js, D3.js, and Alchemy SDK as a learning project.
Built while learning about ML and 3D visualization. Uses NASA API, TensorFlow.js for basic predictions, and Three.js for interactive visualizations. A fun project to explore ML concepts outside finance.
Study project combining textual data mining with technical analysis and portfolio theory for automated trading strategies.
GPU-accelerated image processing using wavelet transformation and parallel algorithms for progressive graphics file format optimization.
Portfolio management and trend analysis system developed for Dufour Capital AG, combining financial mathematics with web technologies.
Open to conversations about AI systems, fintech engineering, or agent architecture.