Head of Infrastructure
General Compute · San Francisco
Infrastructureremotelead
At a glance
Highlights
- Own the infrastructure layer of a neocloud running alternative AI chips.
- Build gateway, routing and observability for 5-7x faster token generation.
- Grow from hands-on first six months to leading a heterogeneous fleet.
Ideal candidate
A hands-on infrastructure leader who thrives early-stage and obsesses over tail latency. You want end-to-end ownership, close vendor partnership, and building on-call culture from zero.
Requirements
- 7+ years in infrastructure, SRE, or platform engineering including at an inference, ML, or HPC shop
- Hands-on with Kubernetes at production scale including debugging complex issues
- Strong instincts for tail latency, p99 and utilization
- Comfortable owning vendor relationships where vendor bugs become production issues
- Track record building observability practices that catch problems
- Experience with on-call through real incidents
- Wants to be first infra hire at an early-stage company
- Experience operating non-NVIDIA accelerators in production
- Background with model-serving stacks such as vLLM, TGI, TensorRT-LLM, SGLang
- Network fabric experience at data-center scale
- Prior experience hiring and managing an infra team
- Comfort at hardware boundary including firmware, drivers, thermals
Lab profile
About General Compute
Neocloud for alternative chips, running fragmented inference on purpose-built silicon.
What they build
- Alternative-chip inference cloud
- Split prefill-decode inference serving
Known for
- Productionizing SambaNova, Cerebras, Positron, d-Matrix hardware
- Rack procurement and data center operations
- ML compiler and model bring-up
Posted · Last seen