Strong systems engineering background in distributed cloud control planes and multi-tenant orchestration at scale.
Comfortable as a high-impact individual contributor rather than a manager.
Proven track record of building reliability from the ground up.
Experience with resource scheduling or bin-packing algorithms for heterogeneous compute pools.
Familiarity with multi-cluster federation or distributed consensus systems like Raft or ZooKeeper.
Ability to navigate hardware heterogeneity and ambiguity.
Genuine interest in joining a small, early-stage company.
Responsibilities
Build and own the control plane for routing, model placement, and scheduling across a mixed ASIC/GPU pool.
Develop the API and serving layer to expose rack capacity as a sellable product.
Integrate reliability and observability into the platform from day one.
Scale the platform proactively to meet future demand.
Collaborate closely with data center deployment and model bring-up teams.
Serve as a founding technical voice in platform architecture discussions.
Manage fleet-wide routing, placement, and capacity, coordinating with the Inference Engineer for model-specific performance.
Benefits
Opportunity to work on a genuinely unsolved technical problem in the field.
No legacy systems to navigate, allowing for innovative solutions.
Be part of a small, dynamic team with significant influence on the company's direction.
Engage in close collaboration with cross-functional teams.
Potential for rapid personal and professional growth in a startup environment.
Full Job Description
About the role
You will build the inference cloud itself - the control plane, API, and serving layer that turn racks into a sellable product. There's no existing platform team to inherit or manage, no legacy system to work around, and no established playbook to follow - just the platform itself to build, with reliability treated as core infrastructure from day one rather than something bolted on after the first outage.The technical problem is also genuinely unsolved elsewhere. The fleet is heterogeneous by design - GPUs for prefill, multiple ASIC vendors for decode - so there's no single-vendor playbook to lean on; you'll be defining how a mixed-hardware inference cloud gets scheduled, routed, and served reliably, in close partnership with the teams standing up the physical fleet.
What you'll do:
Build/own the control plane - routing, model placement, scheduling across a mixed ASIC/GPU pool
Build the API and serving layer exposing rack capacity as a sellable product
Build in reliability and observability from day one
Scale the platform ahead of the demand curve
Partner closely with data center deployment and model bring-up teams
Be a founding technical voice on platform architecture
Work at the boundary with the inference team. Own fleet-wide routing, placement, and capacity; hand off to the Inference Engineer for per-model serving performance (batching, KV-cache, quantization) rather than owning that layer yourself
What we need from you:
Strong systems engineering background on distributed cloud control planes and multi-tenant orchestration at scale (e.g., Kubernetes-style schedulers)
Comfort being a high-impact IC rather than a manager
Track record building reliability from scratch
Experience with resource scheduling or bin-packing algorithms for heterogeneous compute pools
Experience with multi-cluster federation or distributed consensus systems (Raft, ZooKeeper, or similar)
Comfort with hardware heterogeneity/ambiguity
Genuine interest in being an early hire at a ~6-7 person company
Nice-to-haves:
Experience with distributed job schedulers or cluster orchestration systems (Kubernetes, Nomad, Slurm, or similar)
Experience running non-NVIDIA accelerators (TPUs/ASICs) in production
