ML Researcher · Software Developer
Building reliable AI, information systems, and tools for understanding complex systems.
ML researcher and software developer working across retrieval-augmented generation, information trustworthiness, multi-agent behaviour, and computer vision. Her work combines production engineering with published research in deep learning and complex systems modelling.
Selected work
Projects across reliable AI, information systems, complex-systems modelling, and applied machine learning.
ai reliability
A local, reproducible evaluation harness that decomposes RAG answers into atomic claims and compares NLI and LLM-judge assessments of source support.
complex systems
Agent-based simulations of collaboration networks in large software ecosystems, validated against Eclipse, Android, and OpenStack data.
information systems
A production retrieval-augmented document analysis system that produces structured, source-grounded summaries over heterogeneous document collections.
Publications
2025 · accepted
Information and Software Technology
2023 · published
Proceedings of International Conference on Data, Electronics and Computing, Algorithms for Intelligent Systems, Springer
Writing
Long-form explanations built from first principles, experiments, and working code.
Let's dig into selecting the right features for training our models with statistics: variance-based methods, correlation-based methods, ANOVA, and the chi-square test.
It's a fascinating world full of algorithms, all of which have simple origins and lucid explanations. Let's see if you can get inspired enough to code your own neural networks.
The abundance of data these days is overwhelming, and it is growing at an ever-increasing rate. How wonderful would it be if we could use a little of it for our analytics? Let's get started with some of the tools.