I got hooked on astronomy in primary school, from a children's encyclopedia my dad bought us. It had a story about NASA sending Cassini to Saturn to study its rings, and I couldn't understand how anyone could do that. I spent the next years working out how you become the person who does.
That meant switching to science in high school, studying physics and astronomy at the University of Nigeria, Nsukka, and winning an AGNES grant that took me to the South African Astronomical Observatory for two months. I came back wanting to do this for real, and I won the SAAO scholarship to do my PhD in Cape Town. My question there was simple to state and hard to answer: which of the 443,000 radio sources in the MeerKAT Galactic Plane Survey are stars?
Machine learning came sideways. During Covid I interned at Ubenwa, a startup that screens newborns for asphyxia from their cries, doing data analysis and processing on the recordings — not the modelling, the unglamorous work underneath it. It was the same job I'd been doing on telescope data, pointed at something that could affect a baby's life. I started taking every ML course I could, joined the Black and Brilliant AI program, and kept building.
Today I work where those two worlds meet. I've built a system that lets astronomers question a literature no one can read in full, and I submitted my thesis on radio stars in July. I'm looking for roles where careful measurement and working systems both matter.
Hiring an AI engineer? Read the engineering track. Recruiting a radio astronomer? Read the research track.