Hello! I am Dima
Hello! I am Dima
Building scalable
AI solutions
with 
data...
PhD in bioinformatics transforming complex problems into elegant solutions
I'm a |
Currently, I'm a Senior Data Science Consultant atBASE Life Science,
4+ years of industrial experience building ETL pipelines and scalable AI applications. Based in Basel, Switzerland with Swiss Permit C.
Work Experience
Senior Data Science Consultant
BASE Life Science
Basel | 01.2026 - present
Team coordination and development of the agentic GenAI platform structuring clinical trial protocols for a large pharmaceutical company
NLP Engineer
MDPI
Basel | 07.2024 - 12.2025
Co-lead development of the big data pipeline that increased completeness by 10% for over 50M scientific profiles. Developed transformer-based spam detection (3x reduction) and ML model for name annotation (+8% accuracy). Rewrote external database dump processing pipeline in Rust achieving 1500x speedup (1 month → 30min)
Data Scientist
Accenture
Zürich | 05.2022 - 06.2024
Led GenAI stream of 3 developers for 6 months developing 5 GenAI applications. Co-developed patient-trial matching platform extracting health data from EHR. Built ETL pipeline for FHIR/HL7/OMOP medical data with NLP annotation using SNOMED/LOINC ontologies
Research Assistant / PhD Candidate
ETHZ
Zürich | 05.2018 - 04.2022
Developed a novel statistical approach for the extraction of protein correlated motion. Published four first-author papers in bioinformatics
Skills & Expertise
Consulting
Software Development
NLP / GenAI
Data Engineering
DevOps / MLOps
Certifications
- • SAFe PO/PM
- • Neo4j Professional + GDS
- • AWS ML Specialty
- • AWS Solution Architect
- • AWS Cloud Practitioner
Languages
- EnglishFluent
- GermanFluent
- RussianNative
Education
- PhD in BioinformaticsETH Zürich | 2018 - 2022
- MSc ETHETH Zürich | 2016 - 2018
- BSc ETHETH Zürich | 2013 - 2016
Featured Projects
Technical Project
GenAI Clinical Trial Platform
Agentic GenAI platform for structuring clinical trial protocols. Led team of 3 developers building the core AI infrastructure that automates protocol analysis and extraction for a large pharmaceutical company.
Technical Project
Big Data Pipeline - 50M Profiles
Co-led development of big data pipeline that increased data completeness by 10% for over 50M scientific profiles on scilit.com. Built scalable ETL processing system handling massive academic metadata.
Technical Project
Rust Pipeline Optimization
Rewrote external database dump processing pipeline in Rust achieving 1500x speedup - dropping runtime from 1 month to 30 minutes. Dramatically improved data processing efficiency for MDPI.
Technical Project
Transformer Spam Detection
Developed and deployed transformer-based spam detection solution for sciprofiles.com that led to 3x reduction in spam volume. Improved platform content quality through ML-based filtering.