Patrick Audley // A Career in Bioinformatics

I started working at the University of Dundee after I moved to the UK to be with Elizabeth. It was, in retrospect, fated to be. I was spending all my time in Elizabeth’s lab learning everything I could about molecular biology (thanks Elizabeth!) and invariably ended up bumping into the only other people on campus that had an interest in large scale computing. After a very short and informal interview I started in the Computational Biology Dept. with a larger role overseeing all the high-performance computing in the faculty. This doesn’t sound terribly interesting until you consider the research powerhouse that the Life Sciences Faculty contained — to me, it meant being involved in projects with a huge range of research and some incredibly interesting problems to solve.

This job was as large a change as moving to the UK in it’s own way — the pace was terribly different from the corporate world that I’d just left behind. After a brief settling period it was truly a dream job. Looking back, I think I enjoyed Academia most because I got to work with smart people who were always focused on results instead of just passing the time (publish or perish!). I had my own supercomputer (see below) and lots of cool hardware (some of it very strange and wonderful) along with access to all the facilities at the faculty. That last one alone was worth the job alone, which tells you something about me.

For the geeks in the crowd, this marked the first time I had access to over 3TB of storage (eventually over 3PB, yes, that’s 3,000,000 GB) and a few 100GHz (eventually, much, much more) of computing power. The only thing that was a downgrade from my gear at GT was the network which, at it’s peak, reached only around 5 GB/s.

I do have the honour of being, as of leaving the job, the person with the fastest ever NFS implementation that IBM’s HPC teams have seen in terms of actual wire speed file transfers — 2GB/s of actual, real file transfer from a single SAN (fronted with 2 paired p-series NFS servers) over NFS to a cluster of computing nodes was a new sustained load record. Err.. ok, that was pretty geeky, but I was in Academia after all, geekiness is king there.