
Albertus Andito
NLP and AI Researcher | Software Engineer in Brighton, UK
Hi, I’m Albertus Andito. I’m a final year PhD candidate in Informatics at the University of Sussex with experience in natural language processing (NLP), large language models (LLMs), machine learning (ML), and large-scale data systems.
I also currently work part-time as a researcher and software engineer at CASM Technology where we work with non-profit organisations to understand and tackle online harms using NLP.
Also, I’ve been dedicating some of my time to help building and maintaining technology infrastructure of Doctrine UK, an epistemic organisation for Indonesians pursuing PhD in the UK.
I hail from Bandung, Indonesia and currently live in Brighton, UK.
I’m always happy to connect and collaborate.
- LinkedIn albertus-andito
- GitHub albertus-andito
- Instagram @andito_17
- Website albertusandito.com
- Jan 2022 - Present Brighton, UKUniversity of Sussex PhD in Informatics (Natural Language Processing)
- Research on embedding similarity measures and large language models (LLMs) for schema matching and automated assessment of web scraping configurations
- Sep 2017 - Jun 2021 Brighton, UKUniversity of Sussex BSc in Computer Science (with an industrial placement year)
- Achieved First Class Honours (86%)
- Core modules: Software Engineering, NLP, Advanced NLP, Fundamentals of ML, Databases, Program Analysis
- Industrial placement: 1-year software engineering internship at Oracle, AI Applications team
- Final year project: Using dynamic knowledge graph for fake news early detection (Grade: 87%)
- Jan 2022 - Present Brighton, UKPhD Researcher University of Sussex
- Conducting doctoral research in applications of NLP with a focus on schema matching and unsupervised assessment of LLM-generated web scraping configurations
- Developed a novel schema matching approach using self-supervised contrastive learning of sentence embeddings with Hugging Face; benchmarked against and reproduced multiple state-of-the-art competitors through large-scale experiments on HPC clusters (Slurm, multi-GPU)
- Introduced a new research task: unsupervised assessment of LLM-generated web scraping configurations, and designed embedding-based similarity measures to detect incorrect configurations
- Experimented with and evaluated LLMs (via Pydantic AI) in solving the assessment task, comparing their performance to embedding-based methods
- Fully funded doctoral project, supported by University of Sussex and CASM Technology
- Oct 2021 - Present Brighton, UKResearch Software Engineer/Researcher (Part-Time) CASM Technology
- Consultancy working with non-profit organisations in using technologies to detect and understand online harms
- Developed and maintained daily social media data collection and analytics workflows using internal Method52 tool
- Built custom web scrapers to extract data from various news websites for downstream topic modelling and analysis
- Designed techniques to identify networks of related social media accounts given seed users, enhancing coverage of harmful activity detection
- Created interactive client dashboards (Python, Streamlit, Plotly) with metrics and visualisations for analysis and reporting
- Worked directly with clients to translate requirements into deployable, usable technical solutions
- Sep 2021 - Dec 2023 Brighton, UKDoctoral Tutor (Part-Time) University of Sussex
- Delivered 2-4 lab classes per week for Databases and Advanced NLP modules, teaching both undergraduate and MSc students
- May 2021 - Aug 2021 Brighton, UKResearch Assistant Concept Analytics Lab, University of Sussex
- Applied NLP techniques to diary texts for the Mass Observation Visualisation project, enabling geographic visualisation of language use
- Developed a Python library and web API (FastAPI) to extract and query linguistics data (e.g. word and concept frequencies and probabilities, using Spacy), powering an interactive visualisation app
- Oct 2020 - May 2021 Brighton, UKStudent Demonstrator (Part-Time) University of Sussex
- Supported delivery of weekly labs for Introduction to Programming and Further Programming modules
- Jul 2019 - Sep 2020 Reading, UKSoftware Engineer Intern Oracle
- Interned with the AI Apps team, contributing to frameworks that embedded machine learning to Oracle’s enterprise products
- Built and maintained an example application and automated end-to-end testing suite, enabling application developers to adopt framework components more easily
- Implemented new features and maintained the framework using Java, Spring Boot, Grafana, and Prometheus
- Oct 2023 - Present Remote, UKHead of IT Department Doctrine UK (Doctoral Epistemic of Indonesian in the UK)
- Lead a team of IT-focused PhD students in maintaining and expanding the organisation’s digital infrastructure for 800+ members
- Introduced Kanban workflows (Trello) to improve scheduling and delivery of knowledge cluster events
- Directed migration of the organisation’s website from WordPress to a static site generator (Astro), simplifying content structure and enabling richer interconnections between organisational content and entities
- Maintained and developed new features for the member portal web app (MERN stack)
- Supervised the development of a dynamic visualisation dashboard for membership census data
- Jun 2025 - Aug 2025 London, UKICT Literacy Workshop Facilitator SEEAC (Southeast and East Asian Centre)
- Facilitated biweekly workshops for 30 Filipino domestic workers, delivering training in essential ICT skills
- Jan 2022 - Sep 2023 Remote, UKDeputy Head of IT Department Doctrine UK (Doctoral Epistemic of Indonesian in the UK)
- Developed a membership census portal web app used by 800+ members for registration and data updates
- Built and deployed an online election platform to support organisational voting processes
- Maintained and updated the organisation’s WordPress website content
- Oct 2020 - Oct 2021 Remote, UKFull Stack Developer PPI UK (Indonesian Student Association in the UK)
- Developed and deployed a web application to record and manage the database of Indonesian students in the UK
- Implemented a Single Sign-On (SSO) API integrating the database with the organisation’s discussion forum (Vanilla Forum), streamlining member access
- Programming LanguagesPythonJavaJavaScript/TypeScriptSQL
- ML & NLPHuggingFace TransformersPyTorchscikit-learnSpacyLLM (Pydantic AI)
- Web & App DevelopmentMongoDBExpress.jsReactNode.jsStreamlitFastAPIAstro
- Infrastructure & ToolsSlurm/HPCDigitalOceanGitGitHub Actions