daniel@local · zsh
whoami

Daniel Huber, AI Engineering Lead - AI Foundry / Tech Lead, Financial Technology @ Leonteq · Zürich

cat focus.txt

Taking LLM apps and agents from business idea to governed rollout in a regulated financial institution - platform, delivery, and enablement.
Focus: Agent Engineering · RAG · On-prem LLM Serving · Governance & Auditability · Observability
Stack: Python · LangGraph · LiteLLM · Langfuse · C# · 10+ yrs

open agent-engineering.ch

# AI systems journal, topics auto-collected by agent, deployed via GitHub Actions

Daniel Huber

AI Engineering Lead | Financial Technology

Leading Leonteq's AI Foundry: the internal AI platform, the LLM applications and agents running on it, and the AI strategy and team behind it. I embed with business teams, scope their ideas into agent workflows, prototype fast, and carry each build through audit review toward production go-live. Hands-on engineer with 10+ years in financial technology, alongside leading the Sophis core platform team.

About Me

AI engineering lead at Leonteq, driving the AI Foundry: the internal platform teams use to build and govern LLM applications and agents. I proposed the AI strategy to the CIO and lead the deployments running on the platform, hands-on in Python.

The job is a delivery loop: embed with business teams, scope their ideas into agent workflows, prototype fast, and carry each build through governance and audit review toward production. Alongside it I lead the Sophis core platform team and tech-lead the client-onboarding platform.

Over the past decade I've progressed from analyst to director, working across pricing/analytics, regulatory projects (MiFID II, SFTR, FRTB), and platform migrations. Now focused on bridging the gap between traditional fintech and AI-powered workflows.

Experience Highlights

10+
Years Financial Technology
3
Lead Roles in Parallel
24/7
Trading Platform Ownership

Professional Experience

May 2026 - Present

AI Engineering Lead - AI Foundry - Director

Leonteq Securities AG, Zürich | Concurrent with team-lead role

Leading the AI Foundry, Leonteq's internal AI platform and service layer. Three delivery streams run on it: a knowledge app, agent workflows built from business requests, and agents embedded in existing internal applications. I lead all three, hands-on in Python; larger builds run with delivery partners under my project lead.

  • Customer discovery: I run AI-adoption meetings with departments across the firm - legal, quants, client onboarding, settlements, product documentation. Their ideas become quick PoCs, such as a morning briefing for sales, red-message checks, autocall-event proximity, and reinvestment reports. The winners go to my team's delivery pipeline
  • Prototype to rollout: delivered the internal knowledge app, a Leonteq-adapted OpenWebUI with RAG over very large document sets. I built the ingestion pipeline (parsing, chunking, embedding, hybrid vector/keyword indexing); an external partner delivered the main implementation under my technical and project lead. In firm-wide UAT with identity-governed access; production go-live is gated on the firm's AI audit, now in progress
  • Embedded delivery: leading the settlement-operations deployment - incoming settlement emails are analysed and trades pre-matched to validate bookings. Scoped with the back-office team; I run the partner delivery - scoping, debugging, project management
  • Agent foundation: recurring business requests become agent workflows on a LangGraph DeepAgent foundation with an Electron UI. Business teams compose reusable "skills", such as checking a red message against the term sheet and KID
  • Field patterns to platform: LiteLLM as the single governed gateway for every model call, Langfuse tracing, and a governed API-key workflow so no team runs shadow AI. All validated with information security against audit requirements
  • Infrastructure: responsible for the on-prem serving layer - GPU selection with the infrastructure team, clustering H200s over InfiniBand for large open-weight models (my interconnect proposal, approved), and model-to-hardware placement
  • Executive engagement: co-presented the AI strategy and PoCs with the CIO to sales leadership and the wider sales organisation; internal tech talk on AI agents for IT development; growing the AI team - an intern and two graduates join by September across Zürich and Frankfurt
Python Agent Engineering LangGraph / DeepAgent RAG LLM Serving (on-prem GPU) LiteLLM (Governance) Langfuse (Observability) AI Governance & Audit OpenWebUI
Mar 2026 - Present

Tech Lead - Client Onboarding Platform - Director

Leonteq Securities AG, Zürich | Concurrent with team-lead role

Tech lead for the client-onboarding platform, automating compliance and regulatory workflows to reduce manual effort and onboarding risk.

  • Leading development of the onboarding platform (C#, REST API)
  • Coordinating an external development team alongside internal resources
  • Introducing and leading the project team toward AI-assisted development and project workflows
Tech Leadership C# REST API Compliance Automation AI-Assisted Development
Jan 2023 - Present

Team Lead Sophis Core Development - Director

Leonteq Securities AG, Zürich, Switzerland

Leading a team of 4 developers across Zürich and Lisbon on the firm's core trading and risk platform. Primary interface between the technical team and business stakeholders.

  • Delivered Proof-of-Concept: Research Report Analysis Agent - a multi-model pipeline that ingests unstructured research PDFs, identifies relevant underlyings via semantic search, queries the product database, and scores product-to-trend alignment on local LLM infrastructure
  • Hands‑on development and architecture for Sophis platform components used in real‑time trading
  • Designed a distributed P&L attribution workflow (70 parallel processes)
  • Partnered with quants and risk to translate financial requirements into maintainable solutions
  • Level‑3 escalation and incident lead across Zürich, Singapore, and Amsterdam; improved platform stability through structured incident reviews and proactive monitoring
  • Contributor to FRTB implementation across trading desks
Team Leadership Global Operations Reliability Incident Response Cross-System Debugging Platform Stability Distributed Systems Sophis Risque SCRUM LLM/RAG
Apr 2021 - Dec 2022

Senior Software Developer - Director

Leonteq Securities AG, Zürich, Switzerland

Implemented generic booking model for mirror booking, reducing client onboarding complexity. Built Grafana/Kibana monitoring. Key contributor to LIBOR migration.

  • Implemented generic booking model for mirror booking driven by business analysts
  • Reduced client onboarding complexity through standardized booking workflows
  • Contributed to LIBOR migration project
Grafana Kibana Real-time Analytics Data Monitoring
Jan 2016 - Mar 2021

Software Developer - Associate

Leonteq Securities AG, Zürich, Switzerland

Progressed through multiple roles focusing on automation, risk management, and regulatory compliance.

  • 2020–2021: Team member in Sophis version migration (v6.3 to Fusion 7)
  • 2019: Automation tools for Trading & Treasury (C#, WPF, SQL)
  • 2016–2019: Developed analytics platform for instrument pricing coverage; migration to internal quant pricing engine
  • Contributed to regulatory projects (MiFID II, SFTR, 871m)
C# WPF SQL Automation Risk Systems
Oct 2014 - Dec 2015

Software Developer - Analyst

Leonteq Securities AG, Zürich, Switzerland

Focused on reporting automation and distributed system implementation. Automated creation of listed instruments via SmartCo integration.

  • Distributed end-of-day reporting systems
  • Barrier monitoring
  • Automated instrument creation; reduced manual work by ~80%
Automation Distributed Systems Reporting

Projects

Personal projects applying ML/AI and agent development to financial technology

AI & Agent Projects

Academic Projects

Algorithmic Trading and Text-Mining

Feb 2014 - Aug 2014

Study project combining textual data mining with technical analysis and portfolio theory for automated trading strategies.

University of Applied Sciences FHNW
Java Text Mining Information Retrieval Technical Analysis Portfolio Theory

Progressive Graphics File (PGF) on GPU

Feb 2014 - June 2014

GPU-accelerated image processing using wavelet transformation and parallel algorithms for progressive graphics file format optimization.

University of Applied Sciences FHNW
C++ AMP GPU Programming Wavelet Transformation Parallel Algorithms

MyTrendRadar

Sep 2013 - Feb 2014

Portfolio management and trend analysis system developed for Dufour Capital AG, combining financial mathematics with web technologies.

University of Applied Sciences FHNW
Customer: Dufour Capital AG
JavaScript Java Mathematica MySQL Joomla

Reference Architecture

Agent & RAG platforms are the area I focus on most. To show how I approach these systems end to end, here's a generalized reference architecture I put together.

A vendor-neutral enterprise RAG & agent platform. Pick a request flow to trace it through the stack.

Generic reference design, shown for illustration, not a depiction of any specific production system.

Client
User · Browser
Identity
Identity ProviderOIDC / SSO
Interface
Chat UIDirect · KB · Upload
Knowledge Admin UIgoverned uploads
Orchestration
Conversation Memory
Agent / Orchestratormode routing
Document ParserOCR · chunk
Platform
Model Gatewayguardrails · routing · quotas
Observabilitytraces · evals
Model serving
LLM
Embedding Model
Reranker
Data
Vector DBhybrid · ACL-filtered
Object Storage
Ingestion
Ingestion Queue
Embedding Workerchunk · embed · index
Request path Telemetry Data store Async ingestion 1Numbers trace the selected flow in order

Technical Skills

FinTech Domain (10+ Years)

Sophis Risque Structured Products Risk Management Trading Systems Capital Markets

Engineering & Leadership

C# / .NET SQL Distributed Systems Team Leadership Incident Response

Education

2011 - 2014

Informatik-Ingenieur FH, Computer Science

University of Applied Sciences FHNW

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.

Computer Science Software Engineering Algorithms System Design
2009 - 2011

Mathematics Studies

ETH Zürich

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.

Linear Algebra Calculus Probability Theory Statistics

Certificates

Deep Learning Specialization

DeepLearning.AI · March 2026

Neural networks, CNNs, RNNs, sequence models, and deep learning optimization techniques.

View Certificate →

5-Day AI Agents Intensive Course

Google & Kaggle · November 2025

Agent architectures, tool integration, Google ADK. Built a trading strategy agent for the Kaggle competition.

View Badge →

Machine Learning Specialization

Stanford University & DeepLearning.AI · March 2025

Supervised/unsupervised learning, neural networks, deep learning fundamentals.

View Certificate →

Mathematics for ML and Data Science

DeepLearning.AI · June 2025

Linear algebra, calculus, probability, statistics.

View Certificate →

Structured Products Program

IMD Business School · August 2022

Investment strategies, risk management, complex financial instruments.

View Certificate →

Get In Touch

Open to conversations about AI systems, fintech engineering, or agent architecture.