24.11.2025 aktualisiert
100 % verfügbar
Data Scientist | Data Engineer | Bioinformatics
Lollar, Deutschland
Weltweit
Dr. rer. nat.Über mich
I am an data scientist with a background in the pharma/healthcare industry. I specialize in developing data pipelines, automation and analytics solutions. I am a structured team player with several years of experience supporting international and cross-functional teams.
Skills
Amazon Web ServicesAnalyse-ToolsData AnalysisMicrosoft AzureBig DataBioinformatikBiotechnologieCloud ComputingClusteranalyseDatenbankenKonzeptualisierungInformation EngineeringETLRelationale DatenbankenDjango
Short Profile
I am an experienced data engineer with a background in the biotechnology industry. I specialize in developing scalable data pipelines, databases, dashboards, and analytics solutions. I am a structured team player with several years of experience supporting international and cross-functional teams.
Soft Skills
- Hands-on attitude and strong problem-solving skills
- Engaged team player with excellent communication skills
- Expertise in project conceptualization, planning, and milestone development
- Flexible and quick learner
Data Science
- Python, Pandas, Numpy, SciKit, TensorFlow
- Classification
- Clustering Analysis
- Feature Engineering, Model Training and Validation
- AWS SageMaker
LLMs & Agents
- LLM Frameworks (Langchain, Bedrock)
- Model Context Protocol (MCP)
- Embeddings & Vector Databases
- RAG Pipelines and Document Processing
- Model Validation
- Process Automation (N8N)
Cloud/Data Engineering
- SQL
- Django, Flask, RESTful API Development
- Relational Databases: Postgres, AWS Aurora, SQLite
- ETL/ELT & Data Pipelines: AWS Glue, PySpark, Databricks, Athena
- Data Lake & Lakehouse Concepts
- Docker, Fargate, Openshift
- AWS, Azure
- OAuth
UI & Frontend
- Data Apps (Streamlit, Shiny)
- Prototyping (Figma)
Bioinformatics & Genomics
- Genomics Data Analysis
- Transcriptomics and Gene Expression Analysis
- Single Cell Genomics
- Immunoreceptor Analysis
Erfahrung
Berufserfahrung5 - 10 Jahre
Freelancer seit2024
Sprachen
DeutschMutterspracheEnglischverhandlungssicher
Projekthistorie
- Development and validation of machine learning pipelines for classification of patient datasets
- Planning, documentation and communication with non-technical stakeholders
- Development of internal platform for scientific computation and data science
- Frontend conceptualization & developement (Streamlit)
- Cloud-hosted solution for storing and processing clinical trial datasets
- Streamlit-based user interface
- Data governance and audit-ready application setup