Data Science und Engineering | Bioinformatik
- Verfügbarkeit einsehen
- 2 Referenzen
- 90‐95€/Stunde
- 13359 Mitte
- DACH-Region
- de | en | es
- 01.03.2025
Kurzvorstellung
Preferrably working in Biotech / Pharma and logistics
Auszug Referenzen (1)
"E. T. provided a great support to our data retrieval team and managed the signal management system Empirica Signal."
5/2020 – 2/2021
Tätigkeitsbeschreibung
Expert as well as technical consultancy for the provision of the results of the safety databases of various customers within the Merck Pharmacovigilance system.
Covering an the environment of "SQL", "SQL/PLSQL", "IBM Cognos Analytics" and "Spotfire".
Additional Subject Matter Expert in the Oracle Empirica Pharmacovigilance Signal Management application.
- Content translation of the existing requirements of external customers (physicians as well as operative units)
and members of the IT team
- Development and collection of the medical and scientific questions of the "Safety Data Retrieval Team" within the interviews with the team and translation of the questions into technical requirements for the database.
search strategies
- Programming new and improving existing complex SQL statements
- Development of innovative methods for analysis, evaluation and presentation of pharmacovigilance data
(ARISg, Argus Safety).
- Optimization of query operations by creating and quality checking the database output of the reporting and visualization software.
The aim of the activity is to achieve measurable improvements by automating and optimizing existing processes and tools.
Translating stakeholder requirements into validated systems.
Data Mining, IBM Cognos, PL/SQL, Qualitätsmanagement / QS / QA (IT), Signalverarbeitung
Qualifikationen
Projekt‐ & Berufserfahrung
11/2023 – 1/2025
Tätigkeitsbeschreibung
Implementation of LLM based Text comprehension for the user facing suggest.
· Restructure prompt engineering and Vespa content retrieval ranking.
· Design and training of NN and LightGBM based suggest event responses.
· Timeseries forecasting for user preference assessment.
· Scale and integrate LLMs and RAGs into production with MLFlow monitoring.
· Statistical design of new exeriment analysis pipeline.
Amazon Web Services (AWS), Data Science, Mathematischer Statistiker, MLOps, Python
2/2023 – 8/2023
Tätigkeitsbeschreibung
Data Engineer im Online Banking
Quality control and implementation of streaming data ingest approaches.
Implementation via Python and Java
Cloud (allg.), Data Vault, Data Warehousing
4/2021 – 10/2022
Tätigkeitsbeschreibung
Data engineering
End to End Implementation of a data ingesiton pipeline in GCP.
Dataflow and Airflow batch data ingestion.
MPP Warehouse setup and implementation.
Data visualization via Dashboards. Ticketing system setup via Cherwell.
Data quality assurance automation and implementation.
Stakeholder expectation management and requirement translation.
Big Data, Data Science, Data Warehousing, ETL, Google Cloud
5/2020 – 2/2021
Tätigkeitsbeschreibung
Expert as well as technical consultancy for the provision of the results of the safety databases of various customers within the Merck Pharmacovigilance system.
Covering an the environment of "SQL", "SQL/PLSQL", "IBM Cognos Analytics" and "Spotfire".
Additional Subject Matter Expert in the Oracle Empirica Pharmacovigilance Signal Management application.
- Content translation of the existing requirements of external customers (physicians as well as operative units)
and members of the IT team
- Development and collection of the medical and scientific questions of the "Safety Data Retrieval Team" within the interviews with the team and translation of the questions into technical requirements for the database.
search strategies
- Programming new and improving existing complex SQL statements
- Development of innovative methods for analysis, evaluation and presentation of pharmacovigilance data
(ARISg, Argus Safety).
- Optimization of query operations by creating and quality checking the database output of the reporting and visualization software.
The aim of the activity is to achieve measurable improvements by automating and optimizing existing processes and tools.
Translating stakeholder requirements into validated systems.
Data Mining, IBM Cognos, PL/SQL, Qualitätsmanagement / QS / QA (IT), Signalverarbeitung
1/2020 – 3/2020
Tätigkeitsbeschreibung
Implementierung einer Recommendationengine basierend auf vorhandenen Bild und verkaufsdaten.
Der Ansatz basiert auf der Walmart implementation via imagenet based quantitiative preprocessing.
Data Science, Data Mining, Tensorflow, Python
5/2018 – 1/2020
Tätigkeitsbeschreibung
Design und Aufbau einer Elasticsearch Search Engine.
Volltext Content-Suchmaschine für semi-intelligente Useranfragen. Auswertung mittels Text
crosslinking. Data Design und Technische Implementierung als Microservice. Inklusive ETL.
-> Verbesserte Exposition bestehenden Materials, increases NPS score
Implementierung einer Real-time Userperformance Analyse.
Statistische Auswertung von User sessions mit < 0.2 Sekunden delay
-> Verbesserte User interaktion
Statistische Vorhersagen von Userverhalten / Scoring.
Design eines Scoring systems zur vorhersage von realen Testergebnissen ohne vorhandene
Trainingsdaten.
-> Marketingpush mit hoher Organic-Social Marktwirkung.
Sentimentanalyse, AMBOSS.
Klassifikation von eingehenden Userkommentaren mittels Tensorflow.
-> Entlastung des Servicepersonals.
ETL Design / Airflow.
Design von ETL skripten zur Datenaufbereitung und Qualitätskontrolle.
-> Ein verbesserter Datenfluss spart mittelfristig Zeit und Geld
Data Science, Statistiken, Data Mining, Data Warehousing, Deeplearning4j, Python
11/2013 – 11/2017
Tätigkeitsbeschreibung
Forschung in der Bioinformatik
NGS Data analysis
Datawarehousing
Algorythmic development ( Java and Python )
Deep Learning on Genomics
Statistical Analysis
Data Science, Big Data, Maschinelles Lernen
2/2013 – 10/2013
Tätigkeitsbeschreibung
Analysis of NGS data - assembly and alignment,
Annotation of bacterial genomes,
Implementation of a data warehouse solution (Intermine) and
Analysis of proteomics and transcriptomics data
Data Mining, Data Warehousing
Ausbildung
Barcelona, Spanien
BOKU, Wien / NUI Galway
BOKU, Wien
Feldkirch, Austria
Über mich
Zu meinen bisherigen Kunden gehören unter anderem die Otto GmbH, Media Markt Saturn und die Merck KgaA.
Mein Spezialgebiet ist die Kostenreduktion im Datenumfeld, sowie die effiziente implementierung von ML und AI fokusierten Pipelines.
Weitere Kenntnisse
Python / Java / SQL
Erfahrung in GCP, AWS und Azure.
BigQuery / Data Warehousing / Airflow / Jenkins / Kubernetes / Docker
Lehrerfahrung in Biostatistik
Verschiedene Technologien, sowie Unternehmen bei denen diese zur Anwendung kamen:
SOAP, REST, GraphQL (Amboss, Otto, Media Markt)
Data Lake & Data Vault 2.0 (Deutsche Bank)
Tableau, Looker (Media Markt and Amboss)
Bayesian Inference (PyMC3), Descriptive analytics, Genetic algorithms
Spacy, NLTK, LangChain (Amboss, Media Markt, Otto)
ElasticStack, ElasticSearch + Vespa (Amboss, Otto)
VertexAI, Sagemaker, HuggingFace (Amboss, Otto, MMS)
XGBoost, ARIMA, (Amboss, MMS, Otto)
Persönliche Daten
- Deutsch (Muttersprache)
- Englisch (Fließend)
- Spanisch (Gut)
- Europäische Union
Kontaktdaten
Nur registrierte PREMIUM-Mitglieder von freelance.de können Kontaktdaten einsehen.
Jetzt Mitglied werden