I was a software developer in enterprise when I hit a crisis of meaning. During COVID, I found myself following scientific discussions obsessively — and a pre-Nobel panel in 2021 astounded me how much biology had changed since my high school years. I enrolled in a Systems Biology MSc. During my first semester, the hospital needed someone to work on data standardisation by OMOP — I got the job, and never really left clinical genomics after that.

I hold a BSc and MSc from Vilnius University — first in Informatics, then in Systems Biology. The combination was accidental, but turned out to be exactly right: programming fundamentals from the first degree, biological and data thinking from the second. My real training, though, happened on the job - standardising clinical data, building pipelines, learning by doing. I also was heavily involved into volunteering - from being a member of organising teams in various tech conferences to establishing a language exchange community myself.

I build and maintain euGENia — a clinical genomics platform I created for germline and somatic variant analysis, ACMG classification and allele frequency calculation across our patient cohort. I was one of the main contributors to the DigiOne i3 project from Lithuania's side, working on data extraction, cleaning and transformation processes. In practice, my role sits at the intersection of clinical genomics and engineering — I write code, design data models and aim to automate all genomic and data-related processes in our department.

I want to go deeper on data quality and ETL, contribute to open-source projects — particularly within the OHDSI and DIGICORE communities. Also learning Go — bioinformatics deserves faster tools. I want to get on a conference stage to share my experience. More broadly, I want my tools to be practical and applicable in day-to-day working tasks.

Do your job well and don't cut corners — but give yourself time to build the skills properly, because this work is genuinely hard. Clean, well-structured clinical data is not a nice-to-have; it is the foundation that personalised medicine will be built on. The field is moving fast, and the demand for people who truly understand both the biology and the data will only grow. Curiosity and rigour will take you further than any single tool or technology.

People assume genomic data engineering is about algorithms and biology. In reality, a significant part of my work is negotiating with data security departments, figuring out which spelling of a patient's name is correct and extracting diagnoses from HTML files. At some point you realise you've become unexpectedly good at everything — from guessing a patient's sex by their name across different cultures to configuring a server from scratch.