Mirendil
Member of Technical Staff, Inference
$300K–$400K
San Francisco · On-site · Staff · Full-time · Posted Jun 24, 2026
About the job
Own and optimize inference systems serving Mirendil’s frontier models in research and production.
What you'll do
- Build high-throughput, low-latency inference serving systems.
- Optimize inference performance across GPU and accelerator hardware and extend distributed inference frameworks.
- Implement inference-time optimizations and build observability and reliability infrastructure.
Pay
$300,000–$400,000 USD base salary
Tools
GPU, vLLM, SGLang, TensorRT-LLM
AI focus
Develop and optimize inference systems for frontier AI models, including distributed inference, novel architectures, long-context workloads, and agentic inference patterns.
Model-written summary · the original posting is authoritative