About
I’m Stephen, a machine learning researcher based in Cambridge. I work on pre-clinical drug discovery at AstraZeneca, with a particular interest in applying large language models to scientific problems.
Away from work, that interest in computing extends to local LLMs, Linux, and hardware experiments. Recent projects have included getting an Intel Arc GPU running language models in an older NAS and finding another use for an Intel Optane drive. I enjoy digging into how these systems work, including when getting them working takes a few detours.
This blog is where I write those experiments up: what I tried, what worked, and what didn’t. Hopefully some of it saves someone else an afternoon.
Research
My background is in machine learning research. I completed my PhD at Durham University and later held research and postdoctoral roles, including a joint postdoc between AstraZeneca and Mila, before joining AstraZeneca full-time.
You can find my publications on Google Scholar.
Away from the keyboard
Outside computing, I enjoy cycling, skiing, and photography.
Feel free to get in touch on LinkedIn or explore my projects on GitHub.
Views expressed here are my own and don’t represent my employer.