AG logoAndri Gerber

MSc Applied Data Science

Machine Learning and LLM Engineer

I build production-ready AI systems that turn noisy data into reliable decisions.

About Me

Data Scientist and ML Engineer with a clinical background and strong applied AI focus. I build robust, testable systems from ingestion to deployment, with special emphasis on LLM and retrieval-based architectures in constrained environments.

My recent work combines graph-aware retrieval, evaluation-driven experimentation, and on prem infrastructure operation. I focus on delivering systems that are technically sound and practical for real stakeholders.

MSc Applied Information and Data Science (HSLU), GPA 5.6/6
MSc Physiotherapy (BFH), Best Graduate 2022, GPA 5.6/6
Master Thesis: Graph-aware RAG for Innovation Scouting (HSLU/ ETH Zurich / SDSC)
Reproducible Python/SQL/Kafka pipelines with data validation and testing
Secure offline LLM and RAG prototyping
Cross-functional communication with technical and non-technical stakeholders

CV

Experience and education timeline.

Technical Stack

A selection of the Technologies I use in production and research workflows.

Programming Languages

Core implementation and analytics languages.

Python logoPython
R logoR
SQL logoSQL
Bash (Shell)

Data Science and Analytics Libraries

Modeling, statistics, and data science frameworks.

pandas logopandas
NumPy logoNumPy
scikit-learn logoscikit-learn
Keras logoKeras
TensorFlow logoTensorFlow
Statsmodels logoStatsmodels
ggplot2 logoggplot2

Development Environments and Tools

Daily development, notebooks, and collaboration tooling.

Jupyter Notebooks logoJupyter Notebooks
PyCharm logoPyCharm
Visual Studio Code logoVisual Studio Code
RStudio logoRStudio
Anaconda logoAnaconda
Google Colab logoGoogle Colab
Git logoGit
GitHub logoGitHub
Docker logoDocker

Databases and Big Data

Databases, orchestration, and distributed data systems.

MySQL logoMySQL
PostgreSQL logoPostgreSQL
SQLite logoSQLite
MongoDB logoMongoDB
Neo4j logoNeo4j
Apache Spark (PySpark) logoApache Spark (PySpark)
Apache Airflow logoApache Airflow
Azure Data Factory logoAzure Data Factory
Databricks logoDatabricks

Cloud Platforms and BI

Cloud infrastructure and business intelligence tooling.

Microsoft Azure logoMicrosoft Azure
Amazon Web Services (AWS) logoAmazon Web Services (AWS)
IBM Cloud logoIBM Cloud
Google Cloud Platform (GCP) logoGoogle Cloud Platform (GCP)
Tableau logoTableau
Power BI logoPower BI
Microsoft Excel logoMicrosoft Excel
Metabase logoMetabase
Jira logoJira

LLMs and RAG

Retrieval and generation methods used in current AI work.

Hybrid BM25 + Vector Retrieval
ChromaDB logoChromaDB
Flashrank Reranking
Hugging Face Transformers and Hub logoHugging Face Transformers and Hub
Prompting and Chunking
Context Fusion
Citations Handling

Vector Databases and GraphRAG

Dense/sparse storage and graph-based retrieval systems.

Milvus logoMilvus
Weaviate
Qdrant
Pinecone
FAISS
pgvector logopgvector
Knowledge Graphs logoKnowledge Graphs

Fine-Tuning and Model Evaluation

Efficient adaptation and evaluation workflows.

LoRA logoLoRA
QLoRA logoQLoRA
PEFT logoPEFT
Quantization
Model and Prompt Evaluation
Embedding and Reranker Selection

Telemetry and Monitoring

Observability, quality tracking, and operations metrics.

OpenTelemetry logoOpenTelemetry
Prometheus logoPrometheus
Tracing and Logging
Latency and Throughput Monitoring
Token Cost Monitoring
Retrieval Quality Monitoring

Security, Networking, and Deployment

Secure infrastructure and production deployment patterns.

Tailscale logoTailscale
Zero-Trust Overlay Networking
On-Prem Setups
FastAPI and Uvicorn logoFastAPI and Uvicorn
Docker Compose logoDocker Compose
Kubernetes logoKubernetes
vLLM Serving
Dokploy
VM and VPS Operations
Edge Deployments
NVIDIA GPU Scaling logoNVIDIA GPU Scaling

Agentic and Multimodal AI

Orchestration and multimodal processing patterns.

Tool Calling logoTool Calling
Planner and Executor Workflows
Multi-Agent Patterns
Text, Image, and Audio Pipelines

Applied AI Focus

Current focus areas across retrieval systems, secure deployment, and operational AI quality.

Graph-aware RAG

Designing graph-enhanced retrieval paths for explainable innovation scouting and more robust context grounding.

Secure Offline AI Operations

Running LLM and RAG workloads on prem infrastructure with controlled model and artifact handling.

Agentic and Multimodal Prototyping

Building tool-calling workflows and multimodal pipelines that combine text, image, and audio components.

Operational Quality and Monitoring

Tracking latency, throughput, token cost, and retrieval quality to improve reliability in production settings.

Retrieval-Augmented Generation

For explicit questions please email me.

Try asking: "In which projects can you support us?"

Projects

A selected portfolio of my public ML engineering, analytics, and applied research projects during my studies.

Master Thesis - Graph-aware RAG for Innovation Scouting
thesis

Master Thesis - Graph-aware RAG for Innovation Scouting

Master thesis project focused on graph-aware retrieval pipelines and innovation scouting.

Beta Demo
Will be published soon
Advanced Generative AI - Retrieval-Augmented Generation (RAG)
genai

Advanced Generative AI - Retrieval-Augmented Generation (RAG)

End-to-end multilingual RAG pipeline from data ingestion to answer evaluation.

Improving Deezer's Music Recommendation Engine
recsys

Improving Deezer's Music Recommendation Engine

Enhanced collaborative filtering and content models for better music suggestions.

Google Play Store Apps Project
ml

Google Play Store Apps Project

Explores app features to predict what makes a future hit on the Play Store.

Analyzing Accessibility and Pricing in Swiss Pharmacies
healthcare

Analyzing Accessibility and Pricing in Swiss Pharmacies

Highlights regional differences in painkiller availability and cost.

Sex Differences in Falls Among Elderly Community-Dwelling Swiss Population
publichealth

Sex Differences in Falls Among Elderly Community-Dwelling Swiss Population

Population-based survey exploring gender-specific fall risk factors.

Latest Posts

A compact feed for project notes and engineering write-ups.

New posts coming soon

2026-02-08

This section will include technical writing on applied ML systems, data pipelines, and model evaluation.

Let's Collaborate

Send a short message and I will get back to you. You can also connect directly via GitHub, LinkedIn, or email.

Contact Form

Direct Links

Fastest way to reach out or review my latest work.