Riga, Latvia
Computer Systems graduate · Applied machine learning & AI systems
I have hands-on experience building end-to-end AI systems, from data preprocessing and transformer fine-tuning to evaluation and deployment. My bachelor’s thesis applied DistilBERT and Sentence-BERT to customer-support automation, and I’m looking to build on that foundation with LLM, RAG and agentic AI engineering.
About
I’m a Computer Systems graduate from Riga Technical University with hands-on experience building end-to-end AI systems, including data preprocessing, transformer fine-tuning, evaluation and deployment. My bachelor’s thesis compared rule-based, DistilBERT and Sentence-BERT approaches to customer-support automation, benchmarking accuracy, confidence and latency to understand the trade-off between interpretability and precision.
Alongside the thesis, my public GitHub projects cover test automation and data analysis: a Python test-automation framework with a smaller Java suite, run by GitHub Actions, and a SQL and Python learning project on about 99,000 historical e-commerce orders, with 41 automated validation checks and written limitations. Next I want to grow into modern LLM, RAG and agentic AI engineering.
A transformer-based customer-support assistant: DistilBERT intent classification, Sentence-BERT retrieval, a Flask inference service and a Spring Boot dialogue backend, evaluated against a rule-based approach.
In my thesis I compared three approaches on accuracy, confidence and latency. In my Olist analysis I worded findings as associations and listed the limitations.
My Olist analysis runs 41 automated data-validation checks and stops if any fails, and my API test framework runs in GitHub Actions CI.
Skills
Grouped by the kind of work they support. Each card says where the skills come from.
Source: CV
Source: CV
Source: CV · Olist analysis repo
Source: CV · thesis
Source: GitHub · API Test Automation repo (not in CV)
Source: CV · GitHub
Projects
Featured projects with case studies, followed by coursework and learning projects.
A transformer-based conversational AI for customer support, with a comparative evaluation of rule-based, DistilBERT and Sentence-BERT approaches on accuracy, confidence and latency.
A Python test framework with an API layer and a browser-UI layer, run by GitHub Actions on pushes and pull requests to main, with a live Allure test dashboard.
An end-to-end SQL and Python analysis of about 99,000 Brazilian e-commerce orders: cleaning, validated reporting models, business metrics, charts and written findings.
A modelling project: requirements analysis and process models in BPMN, EFFBD and sequence diagrams for support-ticket and incident-handling workflows.
Normalised relational schemas in MySQL, with analytical SQL across multi-entity datasets.
A self-directed, hands-on walkthrough of the Order-to-Cash process (BD9) in SAP S/4HANA Cloud. The repository currently holds a short README and a notes folder.
Education
In progress
Riga Nordic University · Riga, Latvia
Feb 2023 – 2026
Riga Technical University · Riga, Latvia
AI Fundamentals: Foundations for Understanding AI
IBM SkillsBuild · Oct 2026
Generative AI Fundamentals
Databricks Academy · Aug 2025
Agentic AI Builder Certification
Nebius
Claude Code 101
Claude Academy
IELTS Academic
English proficiency
Contact
I’m happy to talk about machine learning, AI engineering (LLMs, RAG and agentic AI), data analysis and test automation. The quickest way to reach me is by email.
