Shpetim Gashi
Software Developer & Data Scientist
- Lienz, Austria
- [email protected]
- GitHub
Profile
I deliver end-to-end solutions combining web development and machine learning: database-backed applications (Python backends, React/Next.js frontends) and ML systems (forecasting, reinforcement learning, optimisation). I have led an applied AI research project from requirements and method selection through experimentation and evaluation. Currently completing an M.Sc. in Data Science and Intelligent Analytics.
Skills
Programming Languages
- Python
- TypeScript
- JavaScript
- SQL
Backend
- Flask
- REST APIs
- Node.js
- Streamlit
Frontend
- React
- Next.js
- TypeScript
Machine Learning & AI
- Time-Series Forecasting
- LSTM
- SARIMA
- Reinforcement Learning (PPO)
- TensorFlow
- PyTorch
- pandas
- NumPy
- Feature Engineering
- Optimisation (PuLP)
Databases & Data
- PostgreSQL
- Data Pipelines
- Power BI
- EDA
- Statistical Validation
Testing
- pytest
- pytest-cov
- Playwright
- Vitest
DevOps & Tooling
- Git / GitLab
- CI/CD
- Docker
- Jira
- Confluence
- Scrum
- GitHub Issues
Spoken Languages
- German (C2)
- English (C1/C2)
- Albanian (C1)
- French (B2)
Experience
Software Developer, Data Scientist & Project Lead
Sept 2025 - May 2026Full-time role combining hands-on engineering with end-to-end project delivery in an industrial R&D environment. Led an applied AI research project and shipped production web applications and ML systems.
- Built and maintained database-backed web applications end to end - server-rendered Python (Flask) applications, and separately React/Next.js (TypeScript) frontends - covering REST APIs, authentication flows and relational persistence.
- Developed forecasting and reinforcement-learning prototypes (Python, PyTorch, TensorFlow) and built reproducible evaluation pipelines with clear result traceability and KPI-based benchmarking.
- Designed and ran simulation-based reinforcement-learning experiments for building-technology control, covering environment design, agent training, experiment tracking and evaluation.
- Led an applied AI research project: shaped requirements and roadmap, and ran agile delivery with Jira, Confluence, sprint planning and CI/CD.
- Containerised services with Docker, maintained CI/CD pipelines, and conducted code reviews using Git/GitLab and merge requests to ensure reliability and maintainability.
Junior Developer & Data Scientist (Dual Study Programme)
Sept 2022 - Aug 2025Combined a dual study programme at MCI with practical R&D work at HELLA, contributing to forecasting systems, RL pipelines, BI tooling, and internal web tools.
- Developed time-series forecasting models and evaluation pipelines (Python, pandas, NumPy, TensorFlow), comparing neural and classical statistical approaches against baselines.
- Built Power BI dashboards for product and usage analytics, translating operational data into stakeholder-facing reporting.
Student Representative & Chairperson
Sept 2022 - Jun 2026Elected student representative at programme and institutional level across two universities, concurrent with studies and work.
- Chaired governance meetings, defined agendas, and documented strategic decisions at programme and institutional level across MCI and UAS Kufstein.
Working Student - SAP Data Migration
Jan 2022 - Oct 2022Part-time (50%) role migrating insurance records between SAP systems and supervising a team of working students.
- Migrated large volumes of insurance records between SAP systems, ensuring data quality and consistency throughout the platform transition.
- Entrusted with coordinating and supervising 8 working students, allocating tasks due to strong individual performance.
Technical Consultant
Oct 2020 - Sept 2021Customer-facing technical consultancy delivering structured solutions with high satisfaction ratings.
- Analysed customer requirements and delivered structured technical solutions in direct customer-facing settings; produced documentation and achieved a 9.6/10 average customer satisfaction rating.
Salesperson & Team Assistant
Mar 2013 - Oct 2020Long-tenure retail role progressing to team assistant, supporting KPI monitoring, operational planning, and a cost-reduction project.
- Co-managed teams of 9-18 and supported KPI monitoring and operational planning across multiple departments.
- Led a restructuring project that reduced operational costs by 10% and increased seasonal sales by 25%.
Selected Projects
This site. A single-source-of-truth architecture where all CV data lives in one schema-validated YAML file that drives the rendered CV, the project pages, with a playable 16-bit game CV in Phaser in development against the same data. Token-based design system with dark and light themes, a four-stage CI pipeline, and continuous deployment with per-PR previews.
Simulation-based reinforcement-learning experiments for control problems in building technology. PPO agents trained with stable-baselines3 and Gymnasium, Radiance-based simulation tooling for the environment, and TensorBoard for experiment tracking - with simulation assumptions and limitations kept explicit.
Decision-support tool that formulates a constrained manufacturing problem as a linear program in PuLP and exposes scenario analysis through Streamlit and Flask interfaces. Packaged with PyInstaller to run without a Python installation, with the optimisation logic covered by pytest.
A university software-engineering project built around a real-world building-technology use case: a maintainable Flask application for collecting and managing structured user feedback, covering authentication and role handling, PostgreSQL persistence, administrative workflows, REST integration, automated testing, containerisation and CI/CD.
Customer-facing platform for configuring products and visualising them in augmented reality. Contributed across UI/UX and user flows, authentication, database-backed features, CI/CD and quality review, in a TypeScript/Node stack. Agentic coding workflows were used with human review before integration.
Python and pandas tool that groups, transforms and prepares structured work-log data for recurring reporting, replacing a repeated manual preparation step with a consistent, ready-to-review output.
Time-series forecasting pipeline built in two passes: ARIMA/SARIMA baselines with statsmodels first, LSTM models in TensorFlow/Keras about a year later. Evaluation was baseline-oriented throughout, asking whether the added model complexity was justified at all.
Repeatable web data collection and parsing workflows in Python: Selenium for browser automation, BeautifulSoup for HTML parsing and requests for HTTP-based collection, producing structured datasets for downstream analysis.
Education
M.Sc. Data Science and Intelligent Analytics
Sept 2025 - PresentCertificate - Agile Project Management (Scrum)
Dec 2024 - Jan 2025Certificate - Data Science Summer School
Jul 2023 - Aug 2023B.Sc. Smart Building Technologies
Sept 2022 - Jul 2025High School Diploma (Abitur)
Sept 2004 - Jun 2013