One tool I built cut a client's end-of-day admin from 1.5 hours to under 10 seconds.
My final ML training project there predicted term-deposit signups from a Portuguese bank's phone campaigns.
I also tuned YOLOv5 for real-time helmet detection, hitting 35 FPS on an NVIDIA Jetson Nano.
As an intern I replaced manual invoice entry with invoices generated in Python.
Artificial Intelligence Engineer at CellaNova Technologies
I build full-stack systems with RAG pipelines and deploy them on AWS.
One tool I built cut a client's end-of-day admin from 1.5 hours to under 10 seconds.
My final ML training project there predicted term-deposit signups from a Portuguese bank's phone campaigns.
I also tuned YOLOv5 for real-time helmet detection, hitting 35 FPS on an NVIDIA Jetson Nano.
As an intern I replaced manual invoice entry with invoices generated in Python.
Artificial Intelligence Engineer at CellaNova Technologies
I build full-stack systems with RAG pipelines and deploy them on AWS.
One tool I built cut a client's end-of-day admin from 1.5 hours to under 10 seconds.
My final ML training project there predicted term-deposit signups from a Portuguese bank's phone campaigns.
I also tuned YOLOv5 for real-time helmet detection, hitting 35 FPS on an NVIDIA Jetson Nano.
As an intern I replaced manual invoice entry with invoices generated in Python.
By using this service, you agree to the Terms of Service and Privacy Policy.