I support you on implementing AI / ML / Search & Data strategies all the way. From data analysis to the final product: while the big consultancies are good in designing nice power point slides, I help you finish great products and bring them to your customers quickly. All the way with a focus on enabling your team.
I am bringing over 12 years of industry experience in the fields of data science and ml / data / search / backend engineering. During this time I have implemented efficient and effective solutions in high-traffic environments and helped companies reach significant increases in revenue, improve and speed-up their a/b testing setup, develop data and ML strategies and increase customer satisfaction.
Join Recent Happy Customers!
Services
Data Analysis & Consulting
Making insights actionable
AI / ML Projects
Improving your Search (and your AI system with it)
Evaluations, Evaluations, Evaluations
Continuous Experimentation, Feedback & Growth
Development of scalable, efficient solutions
Knowledge Sharing
Team Building
Talks / Workshops
MICES (Berlin) (2019)
Jens Kuersten & Andreas Wagenmann

Talk about offline evaluation in e-commerce search I gave with Jens Kürsten. We described our evaluation approach in Germany's biggest online retailer, Otto.de

MICES (Berlin) (2020)
Ángel Maldonado, Andreas Wagenmann, Sergej Spomer

Angel, Sergej and myself joining forces to give a workshop with diverse group of designers, developers and data scientists about personalized search experiences that evokes trust in users. As such, tackles the gap of privacy concerns and personalized experiences.

Haystack LIVE! (Online) (2022)
Andreas Wagenmann

In this talk I describe the open source project Kolibri that I created. Kolibri in general is an execution framework that syncronizes via cloud storage, yet the particular use case here is for efficient high-throughput offline evaluations of search systems.

Ethics in eCommerce Summit (London) (2023)
Andreas Wagenmann, Ramiro Álvarez, Ana García

For this talk I teamed up with Ramiro and Ana to describe solutions to the perceived gap between innovation and responsibility. The gap results from the huge hunger for data that is inherent to newest ML / AI approaches. We desribe the shift from centralization to decentralization and show specific approaches for great, privacy-preserving customer-experiences.

Flexible Stack
Amazon Web Services (AWS)
Google Cloud
LLM
Big Data
A/B Testing
NLP
Conformal Prediction
MLFlow
Apache Airflow
Argo
Terraform
Python
Scikit-Learn
Pandas
Polars
Apache Spark
Google BigQuery
AWS SageMaker
XGBoost
LightGBM
SQL
Databases
Docker
Kubernetes
Helm Charts
ElasticSearch
Solr
Java
Scala
Python
Clojure
JavaScript
Agile
Spring Framework
REST
MicroServices
Git