Engineering Member – Inference Infrastructure

About the role

As a member of the Compute team, you will focus on GPU workload scheduling and inference serving optimization. You will partner with inference, scalability, and infrastructure teams to improve throughput, latency, and overall system stability for research and reinforcement‑learning workloads.

Key responsibilities

• Design and develop an internal scheduling system that maximizes GPU utilization across the company.
• Build APIs and tooling to manage the lifecycle of GPU workloads and troubleshoot failures.
• Improve the inference control plane to accelerate model deployment and request serving.
• Collaborate with research teams to continuously boost research velocity.

Required profile

• Strong programming skills in Go or comparable languages.
• Solid systems‑engineering background in distributed systems, schedulers, or high‑throughput data planes.
• Production experience with Kubernetes internals (controllers, informers, operators).
• Bias toward observability and debuggability in production environments.

Required skills

• Go
• Kubernetes (controllers, informers, operators)
• Distributed systems
• Schedulers and control planes
• High‑throughput data plane engineering
• Observability and debugging tools

What we offer

• Fully remote work with flexible hours
• 37 days of vacation & holidays per year
• Health‑insurance allowance for you and dependents
• 16 weeks of fully‑paid parental leave
• Well‑being, learning, and home‑office allowances
• Company‑provided equipment and frequent team get‑togethers
• Diverse, inclusive, people‑first culture