Rhea Saldanha
SML Engineer at Everline Software · Ray, model serving
- Everline Software
- Bengaluru, India · IST (UTC+5:30)
- 2+ years experience
- IIT Hyderabad
- English, Hindi, Kannada
Messaging unavailable
Overview
I've spent 2 years on ML infrastructure, now at Everline Software. Cut p99 latency on the ML platform services from 860ms to 69ms. I host a monthly meetup on ML infrastructure.
Good reasons to reach out
- Questions about recommendation systems
Please don't message about
- SEO and link-building offers
- Data broker offers
- Unpaid work or spec projects
Replies between meetings, usually same day
Skills
model servingPyTorchKubeflowRayfeature storesPython
Experience
- ML EngineerOct 2024 - PresentEverline Software · 2 yr · Full-time · Bengaluru, India
- Wrote the metric definitions the leadership team reviews every week.
- Shipped a ranking change that increased conversion 4.3%.
- Replaced 87 hand-built dashboards with one metrics layer people trust.
Projects
Conference talk: lessons from recommendations
2025What went wrong and what worked while scaling recommendation systems.
References
No references yet.
Education
- IIT HyderabadB.Tech, Electronics and Communication2019 - 2023
Details
Compensation expectations
What they are targeting for their next role.
Visible to connections
Direct contact details
Direct email and a scheduling link.
Visible to connections