Job Tracker
Poolside — Member of Engineering (Inference Infrastructure)
Saved
Status
- Added
- 24 September 2026
- Location
- Remote (EMEA)
- Description
- Poolside is building toward AGI through intelligence systems built for software development, with a team distributed across Europe and North America (monthly in-person gathering in Paris). Role: working in the compute team on GPU workload scheduling and inference serving optimization. Partner with the inference team to improve inference throughput/latency for evals and reinforcement learning; collaborate with the scalability team on stabilizing large-scale fault-tolerant training; work with the infra team to keep GPU nodes healthy and fully utilized. Mission: optimize GPU utilization across the company and deliver a stable, scalable inference serving stack for Poolside's researchers. Responsibilities: design and develop an internal scheduling system to maximize GPU utilization; build API and tooling to manage the lifecycle of GPU workloads and troubleshoot failures; design and improve the inference control plane to speed up model deployment and inference request serving; collaborate with research to continuously improve research velocity. Skills & experience: strong programming skills in Go or similar languages; strong systems engineering background (distributed systems, schedulers, control planes, or high-throughput data planes); production experience with Kubernetes internals (controllers, informers, operators, not just deploying to it); bias toward observability and debuggability. Plus: experience serving large-scale inference requests. Process: intro call, technical interview(s) with a Member of Engineering, team fit call with People, final interview with a Founding Engineer. Benefits: fully remote & flexible hours; 37 days/year vacation & holidays; health insurance allowance for you & dependents; 16 weeks flexible full-pay parental leave; well-being/learning/home office allowances; company-provided equipment; frequent team get-togethers.