Available for opportunities

Building the infrastructure
between AI and data

Senior Software Engineer specializing in AI tooling, backend systems, and developer tools. I build the plumbing that connects AI agents to real-world data.

// what I do

Three pillars of my work

AI & Search Systems

Semantic search engines, RAG pipelines, MCP servers, agent observability, and agentic workflows connecting LLMs to real data sources.

Backend Engineering

Scalable microservices with .NET, FastAPI, PostgreSQL, and Elasticsearch. Deployed with Docker and CI/CD pipelines.

Developer Tools

Terminal utilities, CLI tools, and open-source productivity software. Built for developers who live in the terminal.

// featured projects

Things I've built

Open-source tools and systems at the intersection of AI infrastructure, backend engineering, and developer experience.

promptscore
$ promptscore analyze prompt.txt --model claude
▸ Profile: claude · 12 rules loaded
▸ Score: 62/100 — 1 error, 3 warnings
▸ Top: missing-task, no-examples

promptscore

Static analysis for LLM prompts

ESLint, but for prompts. Scores a prompt before it reaches the model — flags ambiguity, missing structure, and gaps against model-specific best practices. Deterministic rules, pluggable profiles, zero LLM calls.

TypeScript Node.js CLI YAML Profiles npm
driftcut
$ driftcut evaluate --model gpt-4.1
▸ Sampling 150 prompts across 8 categories...
▸ Quality: 94.2% Latency: -12ms Cost: -$0.03
✓ Decision: PROCEED

driftcut

Early-stop canary testing for LLM model migrations

Decision gating tool that evaluates quality, latency, and cost before committing to a full LLM model swap. Stratified sampling, parallel execution, and an intelligent decision engine.

Python LiteLLM SQLite Async I/O Pydantic
elastic-mcp
$ elastic-mcp --index logs-*
▸ MCP server listening on stdio
▸ Tools: search, semantic_search, aggregate
▸ Resources: 12 indices mapped

elastic-mcp

MCP Server for Elasticsearch

Lets any AI agent — Claude, Copilot, Cursor — query Elasticsearch via natural language. Pure translator between MCP protocol and ES API. The intelligence lives in the client.

C# .NET 10 MCP Protocol Elasticsearch 9 xUnit
logq
$ logq app.log -f
▸ 142,891 records indexed in 0.3s
▸ Filter: level:error @last-1h
▸ 23 matches · 4 clusters found

logq

Fast, interactive log explorer for the terminal

Treats log files as queryable databases. Live filtering, time histograms, JSON drill-down, trace following, pattern clustering. Zero external dependencies.

Go Zero deps Inverted indexes Binary search
steplight
$ steplight trace.json
▸ 42 spans loaded · 3 tool calls · 2 retries
▸ Tokens: 12,840 in / 3,210 out
▸ Total latency: 4.2s · Cost: $0.08

steplight

Local-first trace inspector for LLM agents

Load a trace, inspect what happened, and understand why. Debug agent runs with timelines, tool calls, retries, token usage, latencies, and diagnostics — all from the terminal.

Python Textual Typer OTEL Traces HTML Export

// tech stack

Tools I work with

Languages

C# Python Go TypeScript

Backend

.NET 10 Blazor FastAPI ASP.NET Core

Data & Search

PostgreSQL Elasticsearch SQLite Vector DBs

AI / ML

RAG Pipelines Semantic Search LLM Agents Agent Observability MCP Protocol

DevOps

Docker GitHub Actions Fly.io Cloudflare

// open source

GitHub at a glance

10
Public repos
4
Languages
2
Stars
2013
Coding since

// experience

Where I've worked

Senior Software Engineer

@ Stuttgart IT

Apr 2024 — Present

Leading development of AI-powered solutions and .NET microservices. Building MCP servers and LLM evaluation tooling. Architecting data exchange platforms across distributed systems.

AI Infrastructure .NET 10 MCP Protocol Elasticsearch

Software Engineer

@ Stuttgart IT

May 2019 — Apr 2024

Designed and implemented enterprise-grade APIs and data processing pipelines. Migrated legacy systems to modern .NET architectures. Built internal tools and automation workflows.

.NET Core REST APIs Azure CI/CD

Computer Engineer

@ National Institute of Geophysics and Volcanology

2013 — 2019

Developed real-time monitoring systems and collaborative data platforms for volcanological research. Built infrastructure for tephra observation networks and multi-hazard surveillance.

Data Systems Real-time Monitoring Scientific Computing Research

// get in touch

Let's connect

I'm always interested in discussing AI infrastructure, open-source tooling, and new engineering challenges. Drop me a line or find me on the platforms below.