Observed arrival · 2026-11-10
Ocha Cakramurti’s LLM inference lab
A platform engineer’s portfolio of LLM inference and MLOps work, alongside an interactive lab focused on GPU infrastructure trade-offs.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Engineers building GPU inference platforms
- Worth noticing
- The lab lists a MIG slicing calculator, a traffic-day fleet simulator, and a gateway failover demo spanning three regions.
Field notes
The experience section traces work at Heidi Health from founding infrastructure engineer through later platform and acting engineering-management roles. The lab descriptions make specific operational trade-offs their subject: MIG slices versus whole GPUs, autoscaling during a traffic day, and gateway behavior during an on-demand capacity outage. All three entries are labeled as building, so the extract does not establish that the demos are already usable.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
◉HumanPersonal, local, civic, or handmade
One card from the complete issue