ER
Erik Röntgen AI Engineering & Strategy
Skills Selected Work Philosophy Systems Games The Lab About Contact
System Status: Operational

Building AI agents for complex reality.

I design, build, and deploy production-grade AI solutions — from RAG systems at scale to autonomous agents that solve hard business problems.

Core Expertise

The technology stack I leverage to solve problems.

Advanced RAG

Beyond basic retrieval. I build multi-hop systems, hybrid search, and graph-based retrieval using LangChain and Vector DBs.

Agentic Workflows

Building autonomous agents that can plan, reason, use SQL tools, and execute Python code to answer complex queries.

Fine-Tuning

Adapting open weights (Llama 3, Mistral) to specific domain language and constraints for maximum performance.

Prompt Engineering

Systematic prompt optimization and evaluation (Evals) to ensure reliability and reduce hallucinations.

Frontier Research Focus

  • Spatial Intelligence Moving beyond text to 3D understanding using Gaussian Splatting and NeRFs for scene reconstruction.
  • World Models & Video Exploring JEPA architectures and generative video models to teach agents physics and causality.
  • Embodied Agents Sim-to-Real transfer learning for autonomous navigation and manipulation in unstructured environments.
Discuss Research

Selected Work

Real results from deployed systems.

Biomedical Knowledge

ROSALIND

1.5M+
Articles indexed & searchable

The R&D Knowledge Engine

Retrieval-Augmented Generation over PubMed articles to support literature review and hypothesis exploration.

RAGScale
Finance

AURELIA

Auto
Financial Modeling & Reporting

Autonomous Orchestration

A coordinated group of agents: SQL agent, RAG agent, and Python agent working together to generate reports.

Multi-agentSQL + Python
Governance

RESPONSIBILIBOT

Safe
Compliant AI Interaction

The Guardrail System

Tailored AI assistants with strict governance, PII masking, and hallucination checks.

GuardrailsSecurity

Philosophy

How I approach building AI products.

01

Frame the Problem

AI isn't magic. I start by understanding the data constraints and defining what "good" output looks like.

02

Prototype Rapidly

I build functional prototypes early to validate feasibility using tools like Databricks or local LLMs.

03

Validate & Evaluate

Evaluation is key. I implement automated evals to measure accuracy, latency, and faithfulness.

04

Productionize

Moving from notebook to production means handling errors, rate limits, and monitoring drift.

Systems Arcade

Animated flows for RAG, agent loops, and guardrails.

Open the dedicated systems page to play the RAG + agent animations without clutter.

About Me

Driven by curiosity and code.

The Background

I am a passionate AI Engineer with a deep focus on bridging the gap between research and production. I don't just run models; I build the infrastructure, governance, and user experience around them to create actual value.

ER

Erik Röntgen

AI Engineering Specialist Based in Germany

Contact

Interested in collaborating or discussing AI strategy?

Reach Out

Let's build something.

I am always open to discussing new opportunities, technical challenges, or just geeking out over the latest paper.