# Daniel Fridljand - Personal Website This page contains my professional biography, experience, and blog posts. --- # Daniel Fridljand **Software Consultant** at [TNG Technology Consulting](https://www.tngtech.com/en/) I am a driven software consultant with a strong academic background in mathematics, statistics, and bioinformatics. My passion for machine learning, software development, and statistics has led me to work on projects across diverse domains, including public health, genetics, and oncology. With three years of scientific software development experience and a first-author publication in a high-impact journal, I'm committed to leveraging computational skills to solve real-world challenges. ## Interests - Statistics - Machine Learning - Software Development ## Education - **Msc in Mathematics**, 2023 — University of Heidelberg - **BSc in Mathematics**, 2020 — University of Heidelberg ## Social Links - [Google Scholar](https://scholar.google.com/citations?user=SIoMbdMAAAAJ) - [GitHub](https://github.com/FridljDa) - [LinkedIn](https://www.linkedin.com/in/daniel-fridljand-8707a2208/) --- # Experience ## Software Consultant - Applied AI **TNG Technology Consulting** | Munich, Germany | Dec 2025 — Present * **AI-Powered Email to Order Parsing (May 2026 – present)**: Designing a field-centric email-processing pipeline that resolves customer, site, and service-order data from inbound emails, attachments, and external business-system context before order creation. Built a FastAPI ingestion service and Streamlit review dashboard with ranked candidate values and human-in-the-loop overrides for ambiguous cases. Integrated attachment-aware LLM processing with multimodal fallbacks — text extraction from structured files, vision-capable paths for scanned PDFs and images, and runtime service-catalog classification. * **AI Customer Support Automation (Dec 2025 – Apr 2026, live in production)**: Sole AI engineer owning end-to-end delivery for a cinema-ticketing SaaS enterprise customer — from discovery and architecture through live production rollout in April 2026. *
Production results and architecture
* **Tech Stack**: Python, FastAPI, Streamlit, PydanticAI, Temporal, Langfuse, Snakemake, Microsoft Presidio, Docker, DSPy (with GEPA), MCP. ## Software Consultant - Enterprise Modernization **TNG Technology Consulting** | Munich, Germany | Dec 2024 — Dec 2025 * Member of the platform team modernizing a mission-critical global supply-chain application (Java 8 → 17, JBoss → WildFly) in a multi-year transformation program. * Shipped a [JFrog Artifactory](https://jfrog.com/artifactory/) proxy in 3 days after the work had been repeatedly postponed due to overestimated effort — reduced a recurring CI pipeline runtime from 8 hours to 30 seconds and continues to save developers ~1–2 hours per person per week. * Established DevSecOps governance: integrated [OWASP Dependency-Check](https://owasp.org/www-project-dependency-check/) into the Jenkins CI pipeline and built Grafana dashboards for CVE monitoring, enabling proactive risk visibility for stakeholders. * Migrated an internal virus-scanning service from SOAP to REST with Keycloak authentication; architected fully containerized dev/build environments using Docker and Podman (daemonless, rootless). * Selected for Program Increment (PI) planning sessions in a multinational distributed Scrum team under SAFe, contributing to strategic planning and cross-team coordination. * Co-organized the internal "AI Tool of the Week" blog series, providing weekly summaries of AI advancements including agentic workflows, AI-assisted coding, and multi-modal processing tools. * **Tech Stack**: TypeScript, React, Java 17, Spring Framework, JBoss/WildFly, Oracle DB, Gradle, JUnit, Docker, Podman, Jenkins, SonarQube, JFrog Artifactory, Prometheus, Grafana. ## Research Assistant **ETH Zürich** | Basel, Switzerland | Feb 2024 — Sep 2024 * Researching statistical methods for mutational patterns estimation with tree structures in the lab of [Niko Beerenwinkel](https://bsse.ethz.ch/cbg/group.html) with focus on data from the [Tumor Profiler](https://eth-nexus.github.io/tu-pro_website/). * Lecture on Statistical Models in Computational Biology covering hidden Markov models, EM algorithm, Variational inference. * I developed a novel Bayesian model using Hierarchical Dirichlet Processes (HDP) to analyze mutational signatures by integrating data from evolutionary trees. The model is designed to leverage the phylogenetic relationships between cancer subclones, assuming that evolutionarily closer cells exhibit more similar mutational signature activities. This non-parametric approach learns the number of signatures directly from the data while using the tree structure as a prior to guide the estimation of signature activities. A prototype was implemented and applied to single-cell sequencing data, allowing for the simultaneous discovery of signatures and the mapping of their activities across the cellular phylogeny. My blog post can be found [here](https://danielfridljand.de/post/mutational-signature-with-hierarchical-dirichlet-process/). ## Research Assistant **Stanford University** | Palo Alto, USA | Jul 2023 — Nov 2023 * Led the end-to-end statistical analysis for a landmark study on US health disparities, resulting in a [first-author publication in Nature Medicine](https://www.nature.com/articles/s41591-024-03117-0) * Analyzed the role of air pollution in the race-ethnicity to premature mortality causal chain, under [Pascal Geldsetzer](https://profiles.stanford.edu/pascal-geldsetzer)'s guidance * Spearheaded the project with minimal supervision, [implementing](https://github.com/FridljDa/pm25_inequality) comprehensive statistical analysis in R and synthesizing findings from 150 pertinent publications *
Key achievements and detailed contributions
## Exchange student **Yale University** | New Haven, USA | Sep 2022 — May 2023 Chosen as one of two Master's students to represent the University of Heidelberg in a year-long study abroad program at Yale University. Hosted by the [Applied Mathematics Program](https://applied.math.yale.edu/). Advised by [Smita Krishnaswamy](https://krishnaswamylab.org/). Course work on Geometric & Topological Methods in Machine Learning, Differentiable Manifolds, Deep Learning, Statistical Methods in Human Genetics ## Research Assistant **European Molecular Biology Laboratory** | Heidelberg, Germany | Oct 2021 — May 2022 * Developed IHW-Forest, a scalable solution to the "curse of dimensionality" that previously limited the standard [IHW method](https://bioconductor.org/packages/release/bioc/html/IHW.html) for high-dimensional datasets. * Supervised by [Wolfgang Huber](https://www.huber.embl.de/) and [Nikos Ignatiadis](https://nignatiadis.github.io/). * Designed an innovative stratification algorithm that automatically selects and ranks informative covariates, enhancing robustness to noisy and unknown features in real-world data. * Led the project from inception to dissemination, presenting results at seven scientific events, including invited talks at [Yale University](https://www.yale.edu/), [University of North Carolina at Chapel Hill](https://www.unc.edu/), and a competitively selected oral presentation at [DAGStat 2022](https://www.dagstat2022.uni-hamburg.de/bilder/booklet.pdf) before 100 scholars. * Applied IHW-Forest in a large-scale production analysis of 16 billion genetic tests, utilizing 11 covariates to boost the discovery of significant SNP-histone associations by over 30% compared to alternative methods. * Incorporated concepts from selective inference, machine learning, and empirical Bayes. * Served as a peer reviewer for Bioinformatics Advances and Cell Biology. ## Master Student in Mathematics **Heidelberg University** | Heidelberg, Germany | Oct 2020 — Jun 2023 * Final Grade: 1.0 * Thesis advisor: Dr. Wolfgang Huber (EMBL), Prof. Dr. Jan Johannes * Thesis title: Better Multiple Testing: Using multivariate co-data for hypotheses * Course work on high-dimensional statistics, Probability theory, nonparametric and parametric statistics, Algebraic Topology. ## Exchange Student **Hebrew University of Jerusalem** | Jerusalem, Israel | Sep 2019 — Mar 2020 * Graduate-level coursework in Functional Analysis, Algebraic Combinatorics, and Quantitative Models at the Einstein Institute of Mathematics. ## Bachelor Student in Mathematics **Heidelberg University** | Heidelberg, Germany | Oct 2017 — Sep 2020 * Final grade: 1.4 * Thesis advisor: Prof. Dr. Jan Johannes * Thesis title: Online Estimation of the Geometric Median in Hilbert Spaces * Thesis summary: Mathematically analyzed a novel, efficient algorithm for estimating the geometric median in Hilbert spaces, proving its almost sure consistency, convergence rate, and asymptotic normality. * Minor in Computer Science * Coursework in Statistics, Algorithms and Data Structures, Linear Algebra, Abstract Algebra --- # Publications ## Disparities in air pollution attributable mortality in the US population by race/ethnicity and sociodemographic factors **Authors:** Pascal Geldsetzer, Daniel Fridljand, Mathew Kiang, Eran Bendavid, Sam Heft-Neal, Marshall Burke, Alexander H. Thieme, Tarik Benmarhnia **Journal:** Nature Medicine **Date:** 2024-07-01 **Publication:** [https://www.nature.com/articles/s41591-024-03117-0](https://www.nature.com/articles/s41591-024-03117-0) **Code:** [https://github.com/FridljDa/pm25_inequality](https://github.com/FridljDa/pm25_inequality) **Dataset:** [https://zenodo.org/records/10038691](https://zenodo.org/records/10038691) In the US between 2000 and 2011, over half of the gap in mortality between Black and non-Hispanic White adults can be explained by the fact that Black adults are, on average, more exposed and more susceptible to air pollution than non-Hispanic White adults. --- # Blog Posts ## Architecture of a First-Level Support Automation The four-step pipeline we landed on after iterating in production: a rooted DAG of intents, grouped extraction, weighted-scoring fetch, and a mostly-hardcoded planner with an explicit LLM fallback. **Published:** May 16, 2026 **Tags:** AI, Customer Support, Architecture **Link:** [View post](/post/first-level-support-automation) ## On the Future of Pull Requests in the Age of Agentic Coding **Published:** May 8, 2026 **Tags:** AI, Software Engineering, Agentic Coding **Link:** [View post](/post/future-of-pull-requests) ## Masks and Cross-Attention: Extending Self-Attention **Published:** May 3, 2026 **Tags:** AI, Math **Link:** [View post](/post/masks-and-cross-attention) ## Encoder, Decoder, Both: The Three Transformer Architectures Self-attention is the mechanism. BERT, GPT, and T5 are three different ways to stack it. **Published:** May 3, 2026 **Tags:** AI **Link:** [View post](/post/transformer-architectures) ## From Kernel Regression to Self-Attention: A Line-by-Line Derivation **Published:** April 20, 2026 **Tags:** AI, Math **Link:** [View post](/post/kernel-to-attention) ## Agentic vs Workflow-based AI Workflow win over agents in business process automation. **Published:** April 19, 2026 **Tags:** AI **Link:** [View post](/post/workflow-vs-agent) ## Book Review: Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems Practical, critical review of 'Agentic Design Patterns' — evaluates agent design techniques, code examples, and their real-world usefulness for engineers and researchers. **Published:** March 29, 2026 **Tags:** AI **Link:** [View post](/post/agentic-design-book-review) ## Unite x TUM.ai Data Mining Hackathon: Core Demand Prediction How we tackled Challenge 2 at the Unite x TUM.ai Data Mining Hackathon: fee-aware portfolio optimization for recurring procurement demand, from raw PLI data to a two-stage model and NACE-informed cold start. **Published:** March 8, 2026 **Tags:** Data, ML, Hackathon **Link:** [View post](/post/unite-tum-ai-data-mining-hackathon-core-demand) ## Langfuse in Production: Monitoring, Persistent Traces, and a Self-Improving Codebase How I use Langfuse in an AI support pipeline for monitoring, persisting evaluation runs for later review, closing the loop with a multi-agent triage loop driven by Cursor, and a decision framework for when to fix eval data versus prompts. **Published:** February 25, 2026 **Tags:** AI, Python, Observability **Link:** [View post](/post/langfuse-monitoring-eval-self-improvement) ## Type-Safe Hybrid Workflows with Pydantic AI One Pydantic AI primitive scales across deterministic, LLM-assisted, and agentic steps — with the same typed contract everywhere. **Published:** February 25, 2026 **Tags:** AI, Python **Link:** [View post](/post/pydantic-ai-type-safe-hybrid-workflows) ## Temporal for Human-in-the-Loop: When You Don't Know How Long to Wait How Temporal's durable waits, signals, and deterministic recovery make human-in-the-loop workflows reliable when approval times are unknown. **Published:** February 25, 2026 **Tags:** Software Engineering, Workflows, Temporal, Reliability **Link:** [View post](/post/temporal-human-in-the-loop) ## Strategic Model Selection in Cursor: Balancing Cost and Performance Learn how to optimize your Cursor usage by choosing expensive models for planning and cheap models for execution, with a cost vs performance chart updated daily. **Published:** February 6, 2026 **Tags:** AI, Productivity **Link:** [View post](/post/cursor-model-selection-strategy) ## Orchestrating ML Data Pipelines with Snakemake: A Real-World Case Study How I used Snakemake to manage a complex 19-stage ticket analysis pipeline, leveraging scatter-gather parallelization to efficiently process 2000+ customer support tickets with LLM classification. **Published:** February 6, 2026 **Tags:** Data Engineering, Python **Link:** [View post](/post/snakemake-ticket-analysis-pipeline) ## Prompt Injection I participated in a white hat hacking challenge at Agent Olympics Hackathon Munich 2026. Can you trick my chatbot into revealing the secret password? **Published:** January 24, 2026 **Tags:** AI, Security **Link:** [View post](/post/prompt-injection) ## Stop Prompting, Start Programming with DSPy DSPy is a framework that separates the 'what' from the 'how' in LLM development, moving from brittle prompt engineering to robust software engineering. **Published:** January 2, 2026 **Tags:** AI **Link:** [View post](/post/stop-prompting-start-programming-dspy) ## Useful Resources for AI Agents A curated collection of essential resources for building and deploying AI agents, covering frameworks, best practices, and engineering insights from leading organizations. **Published:** January 2, 2026 **Tags:** AI, Resources **Link:** [View post](/post/useful-resources-for-ai-agents) ## Building My Personal Website: Technical Highlights A deep dive into the technical implementation of my personal website, covering the AI chat interface, markdown context generation, and resume PDF sync from a dedicated CV repo. **Published:** December 7, 2025 **Tags:** Web Development, AI **Link:** [View post](/post/building-my-personal-website) ## Extending HDP for Mutational Signatures: Incorporating Evolutionary Trees An extension of the Hierarchical Dirichlet Process model that incorporates phylogenetic tree structures to capture evolutionary relationships in mutational signature activities. **Published:** September 20, 2024 **Tags:** Science **Link:** [View post](/post/mapping-mutational-signatures-to-trees) ## Mutational signature estimation with Hierarchical Dirichlet Process A mathematically rigorous introduction to mutational signature estimation using Hierarchical Dirichlet Processes, bridging the gap between biological applications and statistical methodology. **Published:** September 15, 2024 **Tags:** Science **Link:** [View post](/post/mutational-signature-with-hierarchical-dirichlet-process) ## Deep Learning-Based Diabetic Retinopathy Detection in Fundus Images A deep learning approach for diabetic retinopathy detection using fundus images, combining binary classification and image segmentation to identify disease presence and quantify key indicators. **Published:** May 1, 2024 **Tags:** Science, AI **Link:** [View post](/post/diabetic-retinopathy-detection)