job
laze
Jobs
Companies
Remote
Sign in
Create alert
Jobs
Companies
Remote
← Back to jobs
LLM inference serving
1 job tagged LLM inference serving
A
Engineering Manager, Inference Routing and Performance
Remote
Visa
Anthropic
continuous batching
coordination planes
prefill/decode disaggregation
KV caching
Trainium
San Francisco
$405k–$485k/yr
Indexed 1 day ago
Apply →