Alan Salomon

Senior Data & AI Engineer

I build production data platforms and LLM systems. Built to survive contact with reality.

Explore my workGet in touch
Try invoice extraction

Work

View all

Systems built to be checked.

Full applications rather than demos: a schema, a database, an API, an interface somebody works in all day, and a test suite that says what the thing is actually worth. Each one is written up with its architecture, the decisions that hold it together, the code that enforces them, and the defects that got through anyway.

Document extraction and AIBuilt and running

One click in Salesforce, and the document becomes data

A document extraction service that is one click inside Salesforce and a FastAPI application on Kubernetes underneath. It identifies the document type, parses it, extracts against a schema written for that type, computes the derived columns the business needs, and writes the result back to the record that triggered it. Input is whatever arrives, including scans and photographs. The model runs inside the company's own Azure tenancy.

PythonFastAPIKubernetesAzure OpenAIAzure FilesLlamaIndexSalesforce
2026Read the case study
Data platformBuilt and running

One number for what an ad is actually worth

Salesforce, Google Ads, LinkedIn Ads, Facebook Ads and website activity extracted into Snowflake, transformed in dbt through staging, marts and a semantic layer, and served to Tableau on a fifteen-minute cycle. Built for a German financial services company serving doctors and healthcare professionals.

AzureKubernetesAirbyteSnowflakedbtTableauSalesforce API
2025Read the case study
Document processingBuilt and running

Invoice extraction, built to be measured

Anyone can build an invoice extractor that works on a clean PDF. This one was built to answer the harder question: how accurate per field, how consistent across repeated runs, and where does it break. It ships as a working review application with the measurement harness underneath it.

PythonFastAPIPostgresSQLAlchemyReactTypeScriptVitepdf.jsDocker
2026Read the case study

Experience

Where the work happens.

  1. AUTO1 Group · Full-time · Berlin

    • Jun 2026 – present

      Senior Analytics Engineer

      Data platform and AI engineering on AWS, dbt and Airflow.

    • Apr 2025 – Jun 2026

      Senior Business Intelligence Manager

    • Dec 2021 – Apr 2025

      Business Intelligence Manager

  2. bookingkit · Part-time · Berlin

    • May 2021 – Dec 2021

      Customer Success Analyst

      Analyzing customers data and creating reports while working closely with various departments like Marketing and Sales.

  3. Teleperformance

    • Mar 2020 – Sep 2020

      Customer Success Engineer

      Providing help regarding technical problems with products and services.

Stack

Data
PythonSQLdbtAirflowPySpark (AWS Glue)PostgreSQLSnowflakeAirbyteGreat ExpectationsTableauSalesforce
AI / LLM
Azure OpenAIAnthropic Claude APILlamaIndexRAG & embeddingspgvectorStructured document extractionLLM evaluation harnesses
Infrastructure & apps
AWS (Glue, DMS, S3, RDS, MWAA)AzureKubernetesDockerTerraformGitHub ActionsFastAPIReact / TypeScriptNext.js

Education

  • M.Sc. Business Engineering · HTW Berlin
  • Diploma in Mechatronics

Writing

Insights & Articles

View all
Reading the document is the demo. The rest is the product.

Sep 13, 2026 · 14 min read

From demo to production. The gap is not the code.

Sep 13, 2026 · 12 min read

Nobody chose 4 GB. It was the default.

Aug 26, 2026 · 9 min read

The AI Museum Experiment

Nine years of AI. Drag through it.

Every milestone that mattered — from the Transformer to today. Watch it play on its own, or take control.

2017
20172026

Playing automatically — or drag to explore →

Enter the world of AI

About me

Alan Salomon

I'm a senior data and AI engineer. I build end-to-end data platforms on AWS, dbt, Airflow and Snowflake, and production LLM systems on top of them: document extraction, retrieval-augmented generation, and the evaluation harnesses that say whether any of it can be trusted. I care about whether things work in production, not just in demos.

I also write about production AI: what it takes to run these systems, where they fail quietly, and what they change for the people who work alongside them. Engineering and writing, for me, are the same investigation from two angles.

Most of what I explore is still open-ended. That's the point.

Feel free to reach out — hello@alansalomon.ai

Alan Salomon