03.09.2024 aktualisiert
100 % verfügbar
Data Engineer
Waldstetten, Deutschland
Nur Remote
Automotive SystemsSkills
Apache AirflowTest AutomationPrompt Engineering
AI Engineering
- Development of multi-agent LLM applications (LangGraph, LangChain, FastAPI, Chainlit)
- LLM evaluation and regression testing (DeepEval, Ragas, custom LLM-as-a-judge metrics, pytest, CI integration)
- Prompt engineering with structured outputs, grounding and measurable regression control
- RAG and Graph-RAG architectures (pgvector, LightRAG), retrieval evaluation and data quality
- Multi-provider LLM integration (Azure OpenAI, Gemini, Groq, Cerebras) incl. cost and latency tracking
- A/B testing and user studies for conversational AI
Data Engineering:
- Design, development, and maintenance of robust and scalable ELT/ETL pipelines using Apache Airflow and Dataform.
- Creation and maintenance of data tests to ensure data integrity and quality.
- Implementation of data ingestion services to integrate new data sources via APIs into data warehouses
- Development of interactive data visualizations and applications for effective presentation of data insights.
- Development of complex data models and data preparation using Python and SQL.
- Contribution to the development and improvement of data warehouse architecture.
- Conducting data analyses and evaluating use cases for external data sources.
API, Apache Airflow, Automotive Software, BigQuery, C/ C++, Cloud, clustering, IBM DOORs, Data-Warehouse, Docker, ETL, Embedded Software, XML, GitHub, Google Cloud Platform, Integrationstests, Jira, JSON, Jupyter Notebook, llms, Machine Learning, Matlab, Excel, Microsoft Office, Power Point, Word, Python, REST-API, SQL, scikit-learn, Simulink, Testautomation
Erfahrung
Berufserfahrung0 - 5 Jahre
Freelancer seit2024
Sprachen
DeutschMutterspracheEnglischverhandlungssicherSpanischGrundkenntnisse
Projekthistorie
Daily Business im Cloud Environment (GCP).
Aufbau und Instanthaltung robuster, skalierbarer ELT/ETL
Pipelines unter Nutzung von Apache Airflow und Dataform.
Entwicklung von Python Services (Cloud Run) für die Data
Ingestion verschiedener Quellen via API und Speicherung
dieser im Data-Warehouse (JSON, JSON nested objects, XML,
CSV, TXT...). Data Cleaning, Wrangling, Testing und
Visualisierung (Jupyter Notebook, Streamlit).
Erstellung komplexer Datenmodelle in SQL (Dataform).
Machine Learning (scikit-learn, clustering embeddings, llms).
Aufbau und Instanthaltung robuster, skalierbarer ELT/ETL
Pipelines unter Nutzung von Apache Airflow und Dataform.
Entwicklung von Python Services (Cloud Run) für die Data
Ingestion verschiedener Quellen via API und Speicherung
dieser im Data-Warehouse (JSON, JSON nested objects, XML,
CSV, TXT...). Data Cleaning, Wrangling, Testing und
Visualisierung (Jupyter Notebook, Streamlit).
Erstellung komplexer Datenmodelle in SQL (Dataform).
Machine Learning (scikit-learn, clustering embeddings, llms).
Testen von Embedded Software - E-Auto: Batteriemanagement.
Unit- und Integrationstests, Testautomation.
Unit- und Integrationstests, Testautomation.
Malteser Hilfsdienst