👋 I’m a research engineer working on and with LLMs in the legaltech space. As a researcher, I investigate LLM-based agents in dialogue settings.

Socials: 🔗 LinkedIn/molnaron ⚙️GitHub/Arotte 🔬 Google Scholar 🐔X/aronmolnr 🤗 HuggingFace/Arotte

Resume: Aron.Molnar.Resume.pdf

Publications

As a research assistant at The Context Lab (University of Aberdeen), I investigate Large Language Model behaviour in dialogue settings.

Attribution & Alignment: Investigating the Effects of Context on Model Utterance Production and Comprehension in Dialogue, Molnar, A., Jumelet, J., Giulianelli, M. & Sinclair, A. Appeared in CoNLL 2023, presented at EMNLP in Singapore. Arxiv.

Analysis of a ferrofluid core differential transformer tilt measurement sensor, T Medvegy, A Molnar, G Molnar, Z Gugolya. Journal of Magnetism and Magnetic Materials 428, 189-193.

Experience

Mid/senior-level engineer with over 6 years of experience in the industry.

AI/LLMs

  • Research Engineer (LLMs) @ Luminance AI – Developing custom LLMs for various legal tasks and scenarios.
  • Research Assistant (Language Modeling) @ University of Aberdeen – Investigating and improving dialogue agents.
  • AI Developer @ HyperDAP (Aberdeen Uni startup) – Developed algorithms to automatically detect and forecast potential oil well failures based on temperature sensor readings.

Software Engineering

I architected and designed a suite of software systems for the University of Aberdeen, IT-Pro, HyperDAP, CollMot and Ericsson. These involved both client-facing and internal and front- and back-end systems. A few examples:

  • Business and inventory management systems for the NHS and defence industry suppliers.
  • Drone fleet management software for drone shows.
  • Internal task automation tools.
  • Telephony application servers responsible for managing millions of daily calls.
  • Area surveying mobile applications for safety consultancies.

Education

BSc Computing Science (2019-2023)

  • University of Aberdeen
  • Graduated with 1st class honours.
  • Thesis: Interpreting Transformer Attention During Next Utterance Dialogue Generation from Human Contexts.

BSc Electrical Engineering (2017-2019)