# Erik Hass

Erik Hass is a remote worker on Himalayas, AI Software Engineer at Markant AG, based in Germany.

Source: https://himalayas.app/@erikhass

```text
AI Software Engineer at Markant AG building an EU regulatory compliance checker with retrieval, reranking, and rule-based evaluation.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | Germany |
| Authorized to work in | Germany |
| Salary expectations | 90k+ EUR |
| Job categories | Artificial Intelligence Engineer |
| Skills | AI, Machine Learning, RAG, Dense Retrieval, BM25, Reciprocal Rank Fusion, Reranking, Large Language Models, Computer Vision, Image Segmentation, Logistic Regression, Vision Transformer, Multi Label Classification, Reinforcement Learning, Synthetic Data Generation |
| GitHub | https://github.com/Er-Hass |

## About

```text
At Markant AG, I built the retrieval and grounding pipeline for an LLM-based EU regulatory compliance checker, combining dense retrieval, BM25, Reciprocal Rank Fusion, and neural reranking across regulatory documents.

I designed the backend and API to orchestrate evaluation of 122 expert-defined rules, with end-to-end checks running in about 12 seconds per document. I also developed a classifier that distinguishes product from lifestyle images using BiRefNet segmentation and logistic regression.

At RUDEL. GmbH, I developed and trained a multi-label dog emotion recognition model using a ViT backbone and a domain-informed loss function. I integrated it into the app backend and automated training and deployment; the model achieved an F1 score of about 0.64.

At Technische Hochschule Ingolstadt, I developed SmartManPy, a production line simulator for synthetic manufacturing data, RL agents, and quality control. I was a co-first author of a peer-reviewed publication based on this work and presented it at ISM 2024.
```

## Experience

### AI Software Engineer (current)

Markant AG. Nov 2025 - Present

```text
Built the retrieval and grounding pipeline for an LLM-based EU regulatory compliance checker, combining dense retrieval, BM25, Reciprocal Rank Fusion and neural reranking across ~4,000 pages of regulatory documents. Designed the backend/API to orchestrate evaluation of 122 expert-defined rules, with end-to-end checks running in ~12 s per document at ~$0.18.
```

Skills: RAG, Dense-Retrieval, BM25, Reciprocal-Rank-Fusion, Reranking, LLM, Backend-Development, API-Design, BiRefNet, Logistic-Regression, Image-Classification

### Organizer of Meetups

Caritas. Nov 2024 - Jan 2026

```text
Organized meetups for young adults with chronic mental health issues.
```

### AI Developer (Working Student & B.Sc. Thesis)

RUDEL. GmbH. Mar 2024 - Aug 2025

```text
Developed and trained a model for multi-label dog emotion recognition with a ViT backbone and domain-informed loss function, using 2,000 labeled images. Integrated it into the RUDEL. app backend using Docker, FastAPI and RunPod, and automated training and deployment with GitLab CI/CD and MLflow.
```

Skills: PyTorch, Vision-Transformer, Multi-Label-Classification, Docker, fastAPI, RunPod, GitLab-CI-CD, MLFlow

### Student Researcher - Institute of AI

Technische Hochschule Ingolstadt. Apr 2022 - Jun 2024

```text
Developed SmartManPy, a production line simulator for generating synthetic manufacturing data with support for RL-agents and quality control. Co-first author of a peer-reviewed publication based on this work, presented at ISM 2024.
```

Skills: Python, Simulation, Reinforcement-Learning, Quality-Control, Research, Publications

### Intern - New Production Concepts

Schaeffler Technologies AG & Co. KG. Aug 2023 - Sep 2023

```text
Prepared and annotated data and evaluated defect-detection ML models. Diagnosed and resolved issues in a non-functional Sim2Real pipeline for synthetic 6D pose-estimation data generation using PoseCNN, Omniverse and CUDA.
```

Skills: Data-Annotation, Defect-Detection, ML-Evaluation, Sim2Real, PoseCNN, Nvidia-Omniverse, CUDA

### Volunteer Assistant

Tafel Lahr. Apr 2020 - Sep 2020

```text
Assisted with food pickup, distribution, preparation and customer service.
```

## Education

### Technische Hochschule Ingolstadt

B.Sc., Artificial Intelligence

```text
Pursuing a B.Sc. in Artificial Intelligence with a thesis on multi-label emotion recognition in dogs using deep learning.
```

## Tech stack

- Python
- PyTorch
- MLflow
- FastAPI
- Transformers
- Linux
- Git
- Docker
- CUDA
- RunPod
- Azure

To contact Erik, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Varun Bukka](https://himalayas.app/@varunbukka): Master Thesis, Forschungszentrum Juelich
- [motaz abuaziza](https://himalayas.app/@motazabuaziza): Equipment Integration Dev, Infineon Technologies
- [Hebah Almorad](https://himalayas.app/@hebahalmorad): Visiting Student Researcher, KAUST
- [Mehar vohra](https://himalayas.app/@meharvohra): Research in AI Dedicated Software Development, IHP – Leibniz Institute for High Performance Microelectronic
- [Debayan Sen](https://himalayas.app/@debayansen): AI Engineer, Hochschule Offenburg
- [Bengali Rabbit](https://himalayas.app/@bengalirabbit): Co Founder & AI Engineer, Where Is My Uni?
- [Shaunak Atul Kanikar](https://himalayas.app/@shaunakatulkanikar): Machine Learning Engineer, Society for the Advancement of Applied Computer Science (GFa
- [Rizeen Musadhik](https://himalayas.app/@rizeenmusadhik): Werkstudent Applied AI Engineer, SEVEN PRINCIPLES GROUP
- [Mahesh Koduri](https://himalayas.app/@maheshkoduri): Junior Software Engineer (Intern), People Tech Group
- [Haaroon Afroz Ognawala](https://himalayas.app/@haaroonafrozognawala): Research Assistant (HiWi) Deep Learning in Computer Vision, Bauhaus University
