What You'll Be Doing

Own the container platform end to end, including image delivery, placement, request routing, scale-up, and scale-to-zero across CPU and GPU.
Solve cold start issues through snapshotting, prewarming, image-layer caching, and other techniques for instant scale-from-zero.
Treat AI workloads as the normal case, managing GPU-backed containers, streaming responses, long-lived connections, and cost-efficient MCP servers.
Write Go code alongside your team and make architecture and difficult implementation decisions.
Grow engineers by setting ownership standards and coaching them beyond their comfort zones.
Manage people aspects such as hiring, performance reviews, growth paths, and providing honest feedback.
Collaborate with Product Managers to translate platform decisions into products that developers want to use.

Requirements

2+ years of real people leadership experience, including hiring, coaching, and growing engineers.
Proven experience shipping production systems in Go.
Experience building container or workload platforms, including orchestration, scheduling, isolation, and request routing.
Strong Linux knowledge including namespaces, cgroups, image layers, and page cache, with comfort below the application layer.
Understanding of multi-tenancy with focus on density, isolation, and fairness among shared fleets.
Significant experience in building complex backend or infrastructure systems.
Track record of partnering with product, design, and business teams to ship software used by real users.
A low-ego, team-first mindset valued by technical peers.

Comprehensive benefits package supporting well-being, growth, and work-life balance.
Benefits may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, meal and transportation allowances, and other location-specific perks.